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

Dataset: Open Web Text

Neuron 1023 in Layer 6

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: 3.6301. Min Range: -3.6301

Max Act: 3.6301. Min Act: -0.1700

Data Index: 3308566 (Open Web Text)

Max Activating Token Index: 727

Text #1

Max Range: 3.6301. Min Range: -3.6301

Max Act: 3.6006. Min Act: -0.1700

Data Index: 6135608 (Open Web Text)

Max Activating Token Index: 253

Text #2

Max Range: 3.6301. Min Range: -3.6301

Max Act: 3.4439. Min Act: -0.1700

Data Index: 3216346 (Open Web Text)

Max Activating Token Index: 304

Text #3

Max Range: 3.6301. Min Range: -3.6301

Max Act: 3.4529. Min Act: -0.1700

Data Index: 6393579 (Open Web Text)

Max Activating Token Index: 839

Text #4

Max Range: 3.6301. Min Range: -3.6301

Max Act: 3.4372. Min Act: -0.1700

Data Index: 5810774 (Open Web Text)

Max Activating Token Index: 130

Text #5

Max Range: 3.6301. Min Range: -3.6301

Max Act: 3.4182. Min Act: -0.1700

Data Index: 3651067 (Open Web Text)

Max Activating Token Index: 400

Text #6

Max Range: 3.6301. Min Range: -3.6301

Max Act: 3.4071. Min Act: -0.1700

Data Index: 6968619 (Open Web Text)

Max Activating Token Index: 893

Text #7

Max Range: 3.6301. Min Range: -3.6301

Max Act: 3.3871. Min Act: -0.1700

Data Index: 967398 (Open Web Text)

Max Activating Token Index: 420

Text #8

Max Range: 3.6301. Min Range: -3.6301

Max Act: 3.3894. Min Act: -0.1700

Data Index: 7911424 (Open Web Text)

Max Activating Token Index: 130

Text #9

Max Range: 3.6301. Min Range: -3.6301

Max Act: 3.3918. Min Act: -0.1700

Data Index: 237737 (Open Web Text)

Max Activating Token Index: 393

Text #10

Max Range: 3.6301. Min Range: -3.6301

Max Act: 3.3664. Min Act: -0.1700

Data Index: 5487997 (Open Web Text)

Max Activating Token Index: 561

Text #11

Max Range: 3.6301. Min Range: -3.6301

Max Act: 3.3603. Min Act: -0.1700

Data Index: 6860658 (Open Web Text)

Max Activating Token Index: 899

Text #12

Max Range: 3.6301. Min Range: -3.6301

Max Act: 3.3548. Min Act: -0.1700

Data Index: 8485699 (Open Web Text)

Max Activating Token Index: 371

Text #13

Max Range: 3.6301. Min Range: -3.6301

Max Act: 3.3486. Min Act: -0.1700

Data Index: 7937202 (Open Web Text)

Max Activating Token Index: 424

Text #14

Max Range: 3.6301. Min Range: -3.6301

Max Act: 3.3538. Min Act: -0.1700

Data Index: 2771925 (Open Web Text)

Max Activating Token Index: 394

Text #15

Max Range: 3.6301. Min Range: -3.6301

Max Act: 3.3304. Min Act: -0.1700

Data Index: 2665876 (Open Web Text)

Max Activating Token Index: 474

Text #16

Max Range: 3.6301. Min Range: -3.6301

Max Act: 3.3491. Min Act: -0.1700

Data Index: 7812667 (Open Web Text)

Max Activating Token Index: 404

Text #17

Max Range: 3.6301. Min Range: -3.6301

Max Act: 3.3357. Min Act: -0.1700

Data Index: 5508093 (Open Web Text)

Max Activating Token Index: 470

Text #18

Max Range: 3.6301. Min Range: -3.6301

Max Act: 3.3357. Min Act: -0.1700

Data Index: 3623266 (Open Web Text)

Max Activating Token Index: 871

Text #19

Max Range: 3.6301. Min Range: -3.6301

Max Act: 3.3298. Min Act: -0.1700

Data Index: 6698087 (Open Web Text)

Max Activating Token Index: 449