< Prev | Home | Model | Random | Next >

Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2543 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 2.9362. Min Range: -2.9362

Max Act: 2.9362. Min Act: -0.1700

Data Index: 8107888 (Open Web Text)

Max Activating Token Index: 358

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.9362. Min Range: -2.9362

Max Act: 2.9300. Min Act: -0.1700

Data Index: 5464509 (Open Web Text)

Max Activating Token Index: 866

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.9362. Min Range: -2.9362

Max Act: 2.9176. Min Act: -0.1700

Data Index: 8793578 (Open Web Text)

Max Activating Token Index: 361

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.9362. Min Range: -2.9362

Max Act: 2.9078. Min Act: -0.1700

Data Index: 6398561 (Open Web Text)

Max Activating Token Index: 85

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.9362. Min Range: -2.9362

Max Act: 2.8896. Min Act: -0.1700

Data Index: 8505383 (Open Web Text)

Max Activating Token Index: 742

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.9362. Min Range: -2.9362

Max Act: 2.8632. Min Act: -0.1700

Data Index: 1995942 (Open Web Text)

Max Activating Token Index: 178

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.9362. Min Range: -2.9362

Max Act: 2.8661. Min Act: -0.1700

Data Index: 4680511 (Open Web Text)

Max Activating Token Index: 965

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.9362. Min Range: -2.9362

Max Act: 2.8570. Min Act: -0.1700

Data Index: 3728914 (Open Web Text)

Max Activating Token Index: 848

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.9362. Min Range: -2.9362

Max Act: 2.8317. Min Act: -0.1700

Data Index: 5036585 (Open Web Text)

Max Activating Token Index: 487

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.9362. Min Range: -2.9362

Max Act: 2.8248. Min Act: -0.1700

Data Index: 7379816 (Open Web Text)

Max Activating Token Index: 585

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.9362. Min Range: -2.9362

Max Act: 2.8237. Min Act: -0.1700

Data Index: 1038967 (Open Web Text)

Max Activating Token Index: 220

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.9362. Min Range: -2.9362

Max Act: 2.8289. Min Act: -0.1700

Data Index: 6021835 (Open Web Text)

Max Activating Token Index: 315

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.9362. Min Range: -2.9362

Max Act: 2.8378. Min Act: -0.1700

Data Index: 2584697 (Open Web Text)

Max Activating Token Index: 388

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.9362. Min Range: -2.9362

Max Act: 2.8148. Min Act: -0.1700

Data Index: 8413067 (Open Web Text)

Max Activating Token Index: 699

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.9362. Min Range: -2.9362

Max Act: 2.8101. Min Act: -0.1700

Data Index: 3969200 (Open Web Text)

Max Activating Token Index: 123

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.9362. Min Range: -2.9362

Max Act: 2.8070. Min Act: -0.1700

Data Index: 5387849 (Open Web Text)

Max Activating Token Index: 134

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.9362. Min Range: -2.9362

Max Act: 2.8103. Min Act: -0.1700

Data Index: 7426179 (Open Web Text)

Max Activating Token Index: 565

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.9362. Min Range: -2.9362

Max Act: 2.8163. Min Act: -0.1700

Data Index: 4385790 (Open Web Text)

Max Activating Token Index: 217

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.9362. Min Range: -2.9362

Max Act: 2.8105. Min Act: -0.1700

Data Index: 4385789 (Open Web Text)

Max Activating Token Index: 285

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.9362. Min Range: -2.9362

Max Act: 2.7908. Min Act: -0.1700

Data Index: 4708095 (Open Web Text)

Max Activating Token Index: 138

Click toggle to see full text

Truncated

Full Text #19