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

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

Neuron 784 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0231. Min Act: -0.0006

Data Index: 550405 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0230. Min Act: -0.0006

Data Index: 768472 (C4 (Web Text))

Max Activating Token Index: 418

Text #2

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0235. Min Act: -0.0006

Data Index: 573746 (C4 (Web Text))

Max Activating Token Index: 460

Text #3

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0229. Min Act: -0.0006

Data Index: 1324061 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0233. Min Act: -0.0006

Data Index: 136808 (C4 (Web Text))

Max Activating Token Index: 392

Text #5

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0230. Min Act: -0.0006

Data Index: 488599 (C4 (Web Text))

Max Activating Token Index: 349

Text #6

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0226. Min Act: -0.0006

Data Index: 1174356 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0220. Min Act: -0.0006

Data Index: 624758 (C4 (Web Text))

Max Activating Token Index: 503

Text #8

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0230. Min Act: -0.0006

Data Index: 1178188 (C4 (Web Text))

Max Activating Token Index: 248

Text #9

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0226. Min Act: -0.0006

Data Index: 564683 (C4 (Web Text))

Max Activating Token Index: 570

Text #10

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0210. Min Act: -0.0006

Data Index: 359011 (C4 (Web Text))

Max Activating Token Index: 1019

Text #11

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0217. Min Act: -0.0006

Data Index: 1229360 (C4 (Web Text))

Max Activating Token Index: 570

Text #12

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0218. Min Act: -0.0006

Data Index: 940661 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0221. Min Act: -0.0006

Data Index: 923654 (C4 (Web Text))

Max Activating Token Index: 351

Text #14

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0216. Min Act: -0.0006

Data Index: 1241466 (C4 (Web Text))

Max Activating Token Index: 32

Text #15

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0220. Min Act: -0.0006

Data Index: 200905 (C4 (Web Text))

Max Activating Token Index: 300

Text #16

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0215. Min Act: -0.0006

Data Index: 801975 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0217. Min Act: -0.0006

Data Index: 1002417 (C4 (Web Text))

Max Activating Token Index: 430

Text #18

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0217. Min Act: -0.0006

Data Index: 724532 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0211. Min Act: -0.0006

Data Index: 262907 (C4 (Web Text))

Max Activating Token Index: 461