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

Dataset: Open Web Text

Neuron 903 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: 0.5578. Min Range: -0.5578

Max Act: 0.5578. Min Act: -0.1700

Data Index: 5304011 (Open Web Text)

Max Activating Token Index: 250

Text #1

Max Range: 0.5578. Min Range: -0.5578

Max Act: 0.5309. Min Act: -0.1700

Data Index: 2357646 (Open Web Text)

Max Activating Token Index: 226

Text #2

Max Range: 0.5578. Min Range: -0.5578

Max Act: 0.5225. Min Act: -0.1700

Data Index: 2586159 (Open Web Text)

Max Activating Token Index: 251

Text #3

Max Range: 0.5578. Min Range: -0.5578

Max Act: 0.5246. Min Act: -0.1700

Data Index: 663536 (Open Web Text)

Max Activating Token Index: 250

Text #4

Max Range: 0.5578. Min Range: -0.5578

Max Act: 0.5229. Min Act: -0.1700

Data Index: 368367 (Open Web Text)

Max Activating Token Index: 249

Text #5

Max Range: 0.5578. Min Range: -0.5578

Max Act: 0.5198. Min Act: -0.1700

Data Index: 2681761 (Open Web Text)

Max Activating Token Index: 284

Text #6

Max Range: 0.5578. Min Range: -0.5578

Max Act: 0.5279. Min Act: -0.1700

Data Index: 405841 (Open Web Text)

Max Activating Token Index: 235

Text #7

Max Range: 0.5578. Min Range: -0.5578

Max Act: 0.5281. Min Act: -0.1700

Data Index: 7315464 (Open Web Text)

Max Activating Token Index: 233

Text #8

Max Range: 0.5578. Min Range: -0.5578

Max Act: 0.5148. Min Act: -0.1700

Data Index: 6027816 (Open Web Text)

Max Activating Token Index: 251

Text #9

Max Range: 0.5578. Min Range: -0.5578

Max Act: 0.5164. Min Act: -0.1700

Data Index: 6868428 (Open Web Text)

Max Activating Token Index: 291

Text #10

Max Range: 0.5578. Min Range: -0.5578

Max Act: 0.5168. Min Act: -0.1700

Data Index: 1668039 (Open Web Text)

Max Activating Token Index: 208

Text #11

Max Range: 0.5578. Min Range: -0.5578

Max Act: 0.5169. Min Act: -0.1700

Data Index: 725942 (Open Web Text)

Max Activating Token Index: 231

Text #12

Max Range: 0.5578. Min Range: -0.5578

Max Act: 0.5182. Min Act: -0.1700

Data Index: 6161864 (Open Web Text)

Max Activating Token Index: 231

Text #13

Max Range: 0.5578. Min Range: -0.5578

Max Act: 0.5121. Min Act: -0.1700

Data Index: 6311856 (Open Web Text)

Max Activating Token Index: 246

Text #14

Max Range: 0.5578. Min Range: -0.5578

Max Act: 0.5057. Min Act: -0.1700

Data Index: 6647858 (Open Web Text)

Max Activating Token Index: 234

Text #15

Max Range: 0.5578. Min Range: -0.5578

Max Act: 0.5174. Min Act: -0.1700

Data Index: 20422 (Open Web Text)

Max Activating Token Index: 239

Text #16

Max Range: 0.5578. Min Range: -0.5578

Max Act: 0.5124. Min Act: -0.1700

Data Index: 8611627 (Open Web Text)

Max Activating Token Index: 236

Text #17

Max Range: 0.5578. Min Range: -0.5578

Max Act: 0.5096. Min Act: -0.1698

Data Index: 1074423 (Open Web Text)

Max Activating Token Index: 240

Text #18

Max Range: 0.5578. Min Range: -0.5578

Max Act: 0.5141. Min Act: -0.1700

Data Index: 5164361 (Open Web Text)

Max Activating Token Index: 189

Text #19

Max Range: 0.5578. Min Range: -0.5578

Max Act: 0.5004. Min Act: -0.1700

Data Index: 4946078 (Open Web Text)

Max Activating Token Index: 262