Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 470 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0259. Min Act: -0.0006

Data Index: 775836 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0260. Min Act: -0.0006

Data Index: 798276 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0227. Min Act: -0.0006

Data Index: 457981 (C4 (Web Text))

Max Activating Token Index: 729

Text #3

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0237. Min Act: -0.0006

Data Index: 374033 (C4 (Web Text))

Max Activating Token Index: 840

Text #4

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0250. Min Act: -0.0006

Data Index: 217048 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0251. Min Act: -0.0006

Data Index: 630003 (C4 (Web Text))

Max Activating Token Index: 266

Text #6

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0244. Min Act: -0.0006

Data Index: 375226 (C4 (Web Text))

Max Activating Token Index: 134

Text #7

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0235. Min Act: -0.0006

Data Index: 373106 (C4 (Web Text))

Max Activating Token Index: 207

Text #8

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0230. Min Act: -0.0006

Data Index: 1164590 (C4 (Web Text))

Max Activating Token Index: 235

Text #9

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0227. Min Act: -0.0006

Data Index: 569340 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0231. Min Act: -0.0006

Data Index: 417644 (C4 (Web Text))

Max Activating Token Index: 853

Text #11

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0215. Min Act: -0.0006

Data Index: 895275 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0229. Min Act: -0.0006

Data Index: 1054452 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0223. Min Act: -0.0006

Data Index: 328931 (C4 (Web Text))

Max Activating Token Index: 925

Text #14

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0222. Min Act: -0.0006

Data Index: 605932 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0212. Min Act: -0.0006

Data Index: 188755 (C4 (Web Text))

Max Activating Token Index: 426

Text #16

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0204. Min Act: -0.0006

Data Index: 134701 (C4 (Web Text))

Max Activating Token Index: 616

Text #17

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0224. Min Act: -0.0006

Data Index: 604249 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0208. Min Act: -0.0006

Data Index: 1050461 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0222. Min Act: -0.0006

Data Index: 359888 (C4 (Web Text))

Max Activating Token Index: 272