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

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

Neuron 296 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: 0.0289. Min Range: -0.0289

Max Act: 0.0289. Min Act: -0.0006

Data Index: 32653 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0284. Min Act: -0.0005

Data Index: 957985 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0271. Min Act: -0.0006

Data Index: 298130 (C4 (Web Text))

Max Activating Token Index: 393

Text #3

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0280. Min Act: -0.0006

Data Index: 31068 (C4 (Web Text))

Max Activating Token Index: 163

Text #4

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0257. Min Act: -0.0006

Data Index: 894842 (C4 (Web Text))

Max Activating Token Index: 825

Text #5

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0249. Min Act: -0.0006

Data Index: 735426 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0246. Min Act: -0.0006

Data Index: 549370 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0239. Min Act: -0.0006

Data Index: 1306773 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0244. Min Act: -0.0006

Data Index: 839154 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0250. Min Act: -0.0006

Data Index: 185064 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0235. Min Act: -0.0006

Data Index: 1033352 (C4 (Web Text))

Max Activating Token Index: 438

Text #11

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0231. Min Act: -0.0006

Data Index: 1031720 (C4 (Web Text))

Max Activating Token Index: 473

Text #12

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0244. Min Act: -0.0006

Data Index: 646375 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0236. Min Act: -0.0006

Data Index: 544421 (C4 (Web Text))

Max Activating Token Index: 327

Text #14

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0229. Min Act: -0.0006

Data Index: 67758 (C4 (Web Text))

Max Activating Token Index: 666

Text #15

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0243. Min Act: -0.0006

Data Index: 1288033 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0231. Min Act: -0.0006

Data Index: 895745 (C4 (Web Text))

Max Activating Token Index: 130

Text #17

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0241. Min Act: -0.0006

Data Index: 203717 (C4 (Web Text))

Max Activating Token Index: 223

Text #18

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0240. Min Act: -0.0006

Data Index: 638966 (C4 (Web Text))

Max Activating Token Index: 513

Text #19

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0224. Min Act: -0.0006

Data Index: 1176163 (C4 (Web Text))

Max Activating Token Index: 834