Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 175 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0277. Min Act: -0.0006

Data Index: 239544 (C4 (Web Text))

Max Activating Token Index: 725

Text #1

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0263. Min Act: -0.0006

Data Index: 1110255 (C4 (Web Text))

Max Activating Token Index: 471

Text #2

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0260. Min Act: -0.0006

Data Index: 1114755 (C4 (Web Text))

Max Activating Token Index: 59

Text #3

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0252. Min Act: -0.0006

Data Index: 107624 (C4 (Web Text))

Max Activating Token Index: 290

Text #4

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0251. Min Act: -0.0006

Data Index: 610449 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0244. Min Act: -0.0006

Data Index: 281147 (C4 (Web Text))

Max Activating Token Index: 123

Text #6

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0241. Min Act: -0.0006

Data Index: 805495 (C4 (Web Text))

Max Activating Token Index: 546

Text #7

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0246. Min Act: -0.0006

Data Index: 649969 (C4 (Web Text))

Max Activating Token Index: 94

Text #8

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0248. Min Act: -0.0006

Data Index: 584825 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0236. Min Act: -0.0006

Data Index: 1011696 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0236. Min Act: -0.0006

Data Index: 626625 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0235. Min Act: -0.0006

Data Index: 590769 (C4 (Web Text))

Max Activating Token Index: 1015

Text #12

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0222. Min Act: -0.0006

Data Index: 1196841 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0232. Min Act: -0.0006

Data Index: 911537 (C4 (Web Text))

Max Activating Token Index: 230

Text #14

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0237. Min Act: -0.0006

Data Index: 421631 (C4 (Web Text))

Max Activating Token Index: 842

Text #15

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0225. Min Act: -0.0006

Data Index: 283915 (C4 (Web Text))

Max Activating Token Index: 638

Text #16

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0225. Min Act: -0.0006

Data Index: 61892 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0225. Min Act: -0.0005

Data Index: 314764 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0224. Min Act: -0.0006

Data Index: 507021 (C4 (Web Text))

Max Activating Token Index: 166

Text #19

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0234. Min Act: -0.0006

Data Index: 1234511 (C4 (Web Text))

Max Activating Token Index: 85