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

Dataset: Open Web Text

Neuron 1903 in Layer 0

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: 1.5656. Min Range: -1.5656

Max Act: 1.5588. Min Act: -0.0650

Data Index: 8143021 (Open Web Text)

Max Activating Token Index: 709

Text #1

Max Range: 1.5656. Min Range: -1.5656

Max Act: 1.5656. Min Act: 0.0246

Data Index: 1634175 (Open Web Text)

Max Activating Token Index: 33

Text #2

Max Range: 1.5656. Min Range: -1.5656

Max Act: 1.5405. Min Act: -0.1391

Data Index: 2315906 (Open Web Text)

Max Activating Token Index: 68

Text #3

Max Range: 1.5656. Min Range: -1.5656

Max Act: 1.5337. Min Act: -0.0124

Data Index: 6267371 (Open Web Text)

Max Activating Token Index: 257

Text #4

Max Range: 1.5656. Min Range: -1.5656

Max Act: 1.5381. Min Act: -0.0234

Data Index: 7193358 (Open Web Text)

Max Activating Token Index: 916

Text #5

Max Range: 1.5656. Min Range: -1.5656

Max Act: 1.5322. Min Act: -0.0352

Data Index: 2322016 (Open Web Text)

Max Activating Token Index: 787

Text #6

Max Range: 1.5656. Min Range: -1.5656

Max Act: 1.5294. Min Act: -0.0495

Data Index: 1605204 (Open Web Text)

Max Activating Token Index: 927

Text #7

Max Range: 1.5656. Min Range: -1.5656

Max Act: 1.5252. Min Act: -0.0323

Data Index: 5986479 (Open Web Text)

Max Activating Token Index: 240

Text #8

Max Range: 1.5656. Min Range: -1.5656

Max Act: 1.5335. Min Act: -0.0738

Data Index: 3536018 (Open Web Text)

Max Activating Token Index: 238

Text #9

Max Range: 1.5656. Min Range: -1.5656

Max Act: 1.5255. Min Act: 0.0072

Data Index: 5768617 (Open Web Text)

Max Activating Token Index: 241

Text #10

Max Range: 1.5656. Min Range: -1.5656

Max Act: 1.5246. Min Act: -0.0829

Data Index: 1780877 (Open Web Text)

Max Activating Token Index: 122

Text #11

Max Range: 1.5656. Min Range: -1.5656

Max Act: 1.5256. Min Act: 0.0247

Data Index: 4904273 (Open Web Text)

Max Activating Token Index: 745

Text #12

Max Range: 1.5656. Min Range: -1.5656

Max Act: 1.5172. Min Act: 0.0035

Data Index: 7403493 (Open Web Text)

Max Activating Token Index: 495

Text #13

Max Range: 1.5656. Min Range: -1.5656

Max Act: 1.5196. Min Act: -0.0130

Data Index: 5986475 (Open Web Text)

Max Activating Token Index: 880

Text #14

Max Range: 1.5656. Min Range: -1.5656

Max Act: 1.5159. Min Act: -0.0894

Data Index: 6819520 (Open Web Text)

Max Activating Token Index: 672

Text #15

Max Range: 1.5656. Min Range: -1.5656

Max Act: 1.5186. Min Act: -0.0899

Data Index: 2166858 (Open Web Text)

Max Activating Token Index: 122

Text #16

Max Range: 1.5656. Min Range: -1.5656

Max Act: 1.5157. Min Act: -0.0938

Data Index: 2694898 (Open Web Text)

Max Activating Token Index: 59

Text #17

Max Range: 1.5656. Min Range: -1.5656

Max Act: 1.5178. Min Act: -0.0845

Data Index: 7525618 (Open Web Text)

Max Activating Token Index: 230

Text #18

Max Range: 1.5656. Min Range: -1.5656

Max Act: 1.5134. Min Act: -0.0988

Data Index: 6864238 (Open Web Text)

Max Activating Token Index: 353

Text #19

Max Range: 1.5656. Min Range: -1.5656

Max Act: 1.5164. Min Act: -0.1284

Data Index: 3818804 (Open Web Text)

Max Activating Token Index: 699