< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 977 in Layer 4

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: 2.3529. Min Range: -2.3529

Max Act: 2.3529. Min Act: -0.1700

Data Index: 4502979 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.3529. Min Range: -2.3529

Max Act: 2.3035. Min Act: -0.1700

Data Index: 2844298 (Open Web Text)

Max Activating Token Index: 251

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.3529. Min Range: -2.3529

Max Act: 2.3013. Min Act: -0.1700

Data Index: 2896137 (Open Web Text)

Max Activating Token Index: 633

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.3529. Min Range: -2.3529

Max Act: 2.2764. Min Act: -0.1700

Data Index: 4702770 (Open Web Text)

Max Activating Token Index: 616

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.3529. Min Range: -2.3529

Max Act: 2.2494. Min Act: -0.1700

Data Index: 3427769 (Open Web Text)

Max Activating Token Index: 293

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.3529. Min Range: -2.3529

Max Act: 2.2451. Min Act: -0.1700

Data Index: 197728 (Open Web Text)

Max Activating Token Index: 10

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.3529. Min Range: -2.3529

Max Act: 2.2495. Min Act: -0.1700

Data Index: 2973068 (Open Web Text)

Max Activating Token Index: 301

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.3529. Min Range: -2.3529

Max Act: 2.2525. Min Act: -0.1700

Data Index: 6818209 (Open Web Text)

Max Activating Token Index: 362

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.3529. Min Range: -2.3529

Max Act: 2.2264. Min Act: -0.1700

Data Index: 6337942 (Open Web Text)

Max Activating Token Index: 573

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.3529. Min Range: -2.3529

Max Act: 2.2279. Min Act: -0.1700

Data Index: 2599541 (Open Web Text)

Max Activating Token Index: 561

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.3529. Min Range: -2.3529

Max Act: 2.2370. Min Act: -0.1700

Data Index: 3014669 (Open Web Text)

Max Activating Token Index: 244

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.3529. Min Range: -2.3529

Max Act: 2.2233. Min Act: -0.1700

Data Index: 2722539 (Open Web Text)

Max Activating Token Index: 425

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.3529. Min Range: -2.3529

Max Act: 2.2024. Min Act: -0.1700

Data Index: 855788 (Open Web Text)

Max Activating Token Index: 992

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.3529. Min Range: -2.3529

Max Act: 2.2162. Min Act: -0.1700

Data Index: 7077142 (Open Web Text)

Max Activating Token Index: 515

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.3529. Min Range: -2.3529

Max Act: 2.2215. Min Act: -0.1700

Data Index: 5737605 (Open Web Text)

Max Activating Token Index: 997

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.3529. Min Range: -2.3529

Max Act: 2.2042. Min Act: -0.1700

Data Index: 6129896 (Open Web Text)

Max Activating Token Index: 758

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.3529. Min Range: -2.3529

Max Act: 2.2069. Min Act: -0.1700

Data Index: 7686986 (Open Web Text)

Max Activating Token Index: 91

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.3529. Min Range: -2.3529

Max Act: 2.2160. Min Act: -0.1700

Data Index: 174711 (Open Web Text)

Max Activating Token Index: 367

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.3529. Min Range: -2.3529

Max Act: 2.2135. Min Act: -0.1700

Data Index: 6355328 (Open Web Text)

Max Activating Token Index: 854

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.3529. Min Range: -2.3529

Max Act: 2.2188. Min Act: -0.1700

Data Index: 6254306 (Open Web Text)

Max Activating Token Index: 469

Click toggle to see full text

Truncated

Full Text #19