< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 2277 in Layer 1

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: 2.0930. Min Range: -2.0930

Max Act: 2.0930. Min Act: -0.1700

Data Index: 2796250 (Open Web Text)

Max Activating Token Index: 691

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.0930. Min Range: -2.0930

Max Act: 2.0578. Min Act: -0.1700

Data Index: 4362143 (Open Web Text)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.0930. Min Range: -2.0930

Max Act: 2.0548. Min Act: -0.1700

Data Index: 5367478 (Open Web Text)

Max Activating Token Index: 174

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.0930. Min Range: -2.0930

Max Act: 2.0468. Min Act: -0.1700

Data Index: 878134 (Open Web Text)

Max Activating Token Index: 315

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.0930. Min Range: -2.0930

Max Act: 2.0522. Min Act: -0.1700

Data Index: 2333106 (Open Web Text)

Max Activating Token Index: 523

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.0930. Min Range: -2.0930

Max Act: 2.0555. Min Act: -0.1700

Data Index: 4417966 (Open Web Text)

Max Activating Token Index: 501

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.0930. Min Range: -2.0930

Max Act: 2.0463. Min Act: -0.1700

Data Index: 4414584 (Open Web Text)

Max Activating Token Index: 29

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.0930. Min Range: -2.0930

Max Act: 2.0260. Min Act: -0.1700

Data Index: 6112679 (Open Web Text)

Max Activating Token Index: 147

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.0930. Min Range: -2.0930

Max Act: 2.0459. Min Act: -0.1700

Data Index: 6071101 (Open Web Text)

Max Activating Token Index: 576

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.0930. Min Range: -2.0930

Max Act: 2.0332. Min Act: -0.1700

Data Index: 3962821 (Open Web Text)

Max Activating Token Index: 522

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.0930. Min Range: -2.0930

Max Act: 2.0200. Min Act: -0.1700

Data Index: 165978 (Open Web Text)

Max Activating Token Index: 389

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.0930. Min Range: -2.0930

Max Act: 2.0326. Min Act: -0.1700

Data Index: 8424273 (Open Web Text)

Max Activating Token Index: 766

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.0930. Min Range: -2.0930

Max Act: 2.0239. Min Act: -0.1700

Data Index: 4664023 (Open Web Text)

Max Activating Token Index: 317

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.0930. Min Range: -2.0930

Max Act: 2.0060. Min Act: -0.1700

Data Index: 3731814 (Open Web Text)

Max Activating Token Index: 152

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.0930. Min Range: -2.0930

Max Act: 2.0025. Min Act: -0.1700

Data Index: 3765362 (Open Web Text)

Max Activating Token Index: 771

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.0930. Min Range: -2.0930

Max Act: 1.9896. Min Act: -0.1700

Data Index: 2529118 (Open Web Text)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.0930. Min Range: -2.0930

Max Act: 1.9950. Min Act: -0.1700

Data Index: 1144672 (Open Web Text)

Max Activating Token Index: 12

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.0930. Min Range: -2.0930

Max Act: 2.0000. Min Act: -0.1700

Data Index: 3908456 (Open Web Text)

Max Activating Token Index: 293

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.0930. Min Range: -2.0930

Max Act: 1.9972. Min Act: -0.1700

Data Index: 4447230 (Open Web Text)

Max Activating Token Index: 520

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.0930. Min Range: -2.0930

Max Act: 2.0097. Min Act: -0.1700

Data Index: 1319257 (Open Web Text)

Max Activating Token Index: 350

Click toggle to see full text

Truncated

Full Text #19