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

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

Neuron 1405 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0378. Min Act: -0.0005

Data Index: 549172 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0303. Min Act: -0.0005

Data Index: 496939 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0293. Min Act: -0.0005

Data Index: 853460 (C4 (Web Text))

Max Activating Token Index: 434

Text #3

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0271. Min Act: -0.0006

Data Index: 529941 (C4 (Web Text))

Max Activating Token Index: 381

Text #4

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0255. Min Act: -0.0005

Data Index: 964763 (C4 (Web Text))

Max Activating Token Index: 311

Text #5

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0248. Min Act: -0.0005

Data Index: 426561 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0247. Min Act: -0.0005

Data Index: 1180907 (C4 (Web Text))

Max Activating Token Index: 647

Text #7

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0247. Min Act: -0.0005

Data Index: 605402 (C4 (Web Text))

Max Activating Token Index: 247

Text #8

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0241. Min Act: -0.0005

Data Index: 263067 (C4 (Web Text))

Max Activating Token Index: 225

Text #9

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0242. Min Act: -0.0005

Data Index: 268446 (C4 (Web Text))

Max Activating Token Index: 408

Text #10

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0235. Min Act: -0.0005

Data Index: 169246 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0245. Min Act: -0.0005

Data Index: 206107 (C4 (Web Text))

Max Activating Token Index: 148

Text #12

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0240. Min Act: -0.0005

Data Index: 486964 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0234. Min Act: -0.0006

Data Index: 90766 (C4 (Web Text))

Max Activating Token Index: 253

Text #14

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0227. Min Act: -0.0006

Data Index: 684544 (C4 (Web Text))

Max Activating Token Index: 348

Text #15

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0233. Min Act: -0.0005

Data Index: 15067 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0238. Min Act: -0.0005

Data Index: 1077153 (C4 (Web Text))

Max Activating Token Index: 752

Text #17

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0226. Min Act: -0.0005

Data Index: 300246 (C4 (Web Text))

Max Activating Token Index: 213

Text #18

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0232. Min Act: -0.0005

Data Index: 1317499 (C4 (Web Text))

Max Activating Token Index: 147

Text #19

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0230. Min Act: -0.0006

Data Index: 227407 (C4 (Web Text))

Max Activating Token Index: 830