Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1539 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0281. Min Act: -0.0004

Data Index: 709682 (C4 (Web Text))

Max Activating Token Index: 401

Text #1

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0233. Min Act: -0.0004

Data Index: 1649362 (Python Code)

Max Activating Token Index: 169

Text #2

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0219. Min Act: -0.0004

Data Index: 1394538 (Python Code)

Max Activating Token Index: 174

Text #3

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0221. Min Act: -0.0004

Data Index: 551800 (C4 (Web Text))

Max Activating Token Index: 383

Text #4

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0218. Min Act: -0.0004

Data Index: 1429209 (Python Code)

Max Activating Token Index: 28

Text #5

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0200. Min Act: -0.0004

Data Index: 743010 (C4 (Web Text))

Max Activating Token Index: 326

Text #6

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0188. Min Act: -0.0004

Data Index: 1475404 (Python Code)

Max Activating Token Index: 18

Text #7

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0187. Min Act: -0.0004

Data Index: 291164 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0181. Min Act: -0.0004

Data Index: 1381514 (Python Code)

Max Activating Token Index: 173

Text #9

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0173. Min Act: -0.0004

Data Index: 1088021 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0174. Min Act: -0.0004

Data Index: 832571 (C4 (Web Text))

Max Activating Token Index: 408

Text #11

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0176. Min Act: -0.0004

Data Index: 1515407 (Python Code)

Max Activating Token Index: 51

Text #12

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0172. Min Act: -0.0004

Data Index: 626218 (C4 (Web Text))

Max Activating Token Index: 736

Text #13

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0171. Min Act: -0.0004

Data Index: 976303 (C4 (Web Text))

Max Activating Token Index: 426

Text #14

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0164. Min Act: -0.0004

Data Index: 1051817 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0161. Min Act: -0.0004

Data Index: 1579510 (Python Code)

Max Activating Token Index: 191

Text #16

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0159. Min Act: -0.0004

Data Index: 1316647 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0157. Min Act: -0.0004

Data Index: 1484057 (Python Code)

Max Activating Token Index: 85

Text #18

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0152. Min Act: -0.0004

Data Index: 1446245 (Python Code)

Max Activating Token Index: 596

Text #19

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0154. Min Act: -0.0004

Data Index: 1544389 (Python Code)

Max Activating Token Index: 17