Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 394 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0328. Min Act: -0.0004

Data Index: 387638 (C4 (Web Text))

Max Activating Token Index: 834

Text #1

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0280. Min Act: -0.0004

Data Index: 155032 (C4 (Web Text))

Max Activating Token Index: 180

Text #2

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0306. Min Act: -0.0004

Data Index: 1171859 (C4 (Web Text))

Max Activating Token Index: 380

Text #3

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0266. Min Act: -0.0004

Data Index: 623640 (C4 (Web Text))

Max Activating Token Index: 581

Text #4

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0300. Min Act: -0.0004

Data Index: 552944 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0281. Min Act: -0.0004

Data Index: 595280 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0275. Min Act: -0.0004

Data Index: 151684 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0260. Min Act: -0.0004

Data Index: 1337831 (C4 (Web Text))

Max Activating Token Index: 777

Text #8

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0285. Min Act: -0.0004

Data Index: 795810 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0230. Min Act: -0.0004

Data Index: 1268482 (C4 (Web Text))

Max Activating Token Index: 495

Text #10

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0256. Min Act: -0.0004

Data Index: 455852 (C4 (Web Text))

Max Activating Token Index: 514

Text #11

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0260. Min Act: -0.0004

Data Index: 745603 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0253. Min Act: -0.0004

Data Index: 241161 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0255. Min Act: -0.0004

Data Index: 159593 (C4 (Web Text))

Max Activating Token Index: 283

Text #14

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0239. Min Act: -0.0004

Data Index: 521460 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0211. Min Act: -0.0004

Data Index: 943663 (C4 (Web Text))

Max Activating Token Index: 580

Text #16

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0239. Min Act: -0.0004

Data Index: 677882 (C4 (Web Text))

Max Activating Token Index: 286

Text #17

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0241. Min Act: -0.0004

Data Index: 1190824 (C4 (Web Text))

Max Activating Token Index: 468

Text #18

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0244. Min Act: -0.0004

Data Index: 223036 (C4 (Web Text))

Max Activating Token Index: 255

Text #19

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0251. Min Act: -0.0004

Data Index: 751270 (C4 (Web Text))

Max Activating Token Index: 322