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

Dataset: Open Web Text

Neuron 1402 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: 4.3242. Min Range: -4.3242

Max Act: 4.3242. Min Act: -0.1700

Data Index: 5392379 (Open Web Text)

Max Activating Token Index: 195

Text #1

Max Range: 4.3242. Min Range: -4.3242

Max Act: 4.3228. Min Act: -0.1700

Data Index: 4308670 (Open Web Text)

Max Activating Token Index: 290

Text #2

Max Range: 4.3242. Min Range: -4.3242

Max Act: 4.2243. Min Act: -0.1700

Data Index: 3610610 (Open Web Text)

Max Activating Token Index: 538

Text #3

Max Range: 4.3242. Min Range: -4.3242

Max Act: 4.2403. Min Act: -0.1700

Data Index: 6230774 (Open Web Text)

Max Activating Token Index: 270

Text #4

Max Range: 4.3242. Min Range: -4.3242

Max Act: 4.2252. Min Act: -0.1700

Data Index: 2158003 (Open Web Text)

Max Activating Token Index: 600

Text #5

Max Range: 4.3242. Min Range: -4.3242

Max Act: 4.1767. Min Act: -0.1700

Data Index: 6745621 (Open Web Text)

Max Activating Token Index: 244

Text #6

Max Range: 4.3242. Min Range: -4.3242

Max Act: 4.1987. Min Act: -0.1700

Data Index: 4990059 (Open Web Text)

Max Activating Token Index: 476

Text #7

Max Range: 4.3242. Min Range: -4.3242

Max Act: 4.1689. Min Act: -0.1700

Data Index: 6682452 (Open Web Text)

Max Activating Token Index: 772

Text #8

Max Range: 4.3242. Min Range: -4.3242

Max Act: 4.1573. Min Act: -0.1700

Data Index: 8478248 (Open Web Text)

Max Activating Token Index: 561

Text #9

Max Range: 4.3242. Min Range: -4.3242

Max Act: 4.1680. Min Act: -0.1700

Data Index: 8505689 (Open Web Text)

Max Activating Token Index: 674

Text #10

Max Range: 4.3242. Min Range: -4.3242

Max Act: 4.1652. Min Act: -0.1700

Data Index: 5044380 (Open Web Text)

Max Activating Token Index: 224

Text #11

Max Range: 4.3242. Min Range: -4.3242

Max Act: 4.1382. Min Act: -0.1700

Data Index: 2678334 (Open Web Text)

Max Activating Token Index: 602

Text #12

Max Range: 4.3242. Min Range: -4.3242

Max Act: 4.1122. Min Act: -0.1700

Data Index: 2527021 (Open Web Text)

Max Activating Token Index: 158

Text #13

Max Range: 4.3242. Min Range: -4.3242

Max Act: 4.1268. Min Act: -0.1700

Data Index: 4902554 (Open Web Text)

Max Activating Token Index: 609

Text #14

Max Range: 4.3242. Min Range: -4.3242

Max Act: 4.1366. Min Act: -0.1700

Data Index: 439002 (Open Web Text)

Max Activating Token Index: 638

Text #15

Max Range: 4.3242. Min Range: -4.3242

Max Act: 4.1179. Min Act: -0.1700

Data Index: 2452675 (Open Web Text)

Max Activating Token Index: 219

Text #16

Max Range: 4.3242. Min Range: -4.3242

Max Act: 4.1348. Min Act: -0.1700

Data Index: 4892138 (Open Web Text)

Max Activating Token Index: 172

Text #17

Max Range: 4.3242. Min Range: -4.3242

Max Act: 4.1313. Min Act: -0.1700

Data Index: 4718148 (Open Web Text)

Max Activating Token Index: 339

Text #18

Max Range: 4.3242. Min Range: -4.3242

Max Act: 4.1363. Min Act: -0.1700

Data Index: 4671110 (Open Web Text)

Max Activating Token Index: 545

Text #19

Max Range: 4.3242. Min Range: -4.3242

Max Act: 4.1194. Min Act: -0.1700

Data Index: 2642207 (Open Web Text)

Max Activating Token Index: 565