Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4400 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0422. Min Act: -0.0002

Data Index: 1010400 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0381. Min Act: -0.0003

Data Index: 1290512 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0348. Min Act: -0.0003

Data Index: 321603 (C4 (Web Text))

Max Activating Token Index: 211

Text #3

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0302. Min Act: -0.0003

Data Index: 244154 (C4 (Web Text))

Max Activating Token Index: 405

Text #4

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0301. Min Act: -0.0003

Data Index: 288542 (C4 (Web Text))

Max Activating Token Index: 549

Text #5

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0291. Min Act: -0.0003

Data Index: 357318 (C4 (Web Text))

Max Activating Token Index: 319

Text #6

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0296. Min Act: -0.0003

Data Index: 110935 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0298. Min Act: -0.0003

Data Index: 122888 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0296. Min Act: -0.0003

Data Index: 948132 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0280. Min Act: -0.0002

Data Index: 1209121 (C4 (Web Text))

Max Activating Token Index: 365

Text #10

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0289. Min Act: -0.0003

Data Index: 862283 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0282. Min Act: -0.0003

Data Index: 890462 (C4 (Web Text))

Max Activating Token Index: 433

Text #12

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0277. Min Act: -0.0003

Data Index: 1012576 (C4 (Web Text))

Max Activating Token Index: 292

Text #13

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0271. Min Act: -0.0003

Data Index: 889693 (C4 (Web Text))

Max Activating Token Index: 550

Text #14

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0273. Min Act: -0.0003

Data Index: 13365 (C4 (Web Text))

Max Activating Token Index: 600

Text #15

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0273. Min Act: -0.0003

Data Index: 556691 (C4 (Web Text))

Max Activating Token Index: 926

Text #16

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0272. Min Act: -0.0003

Data Index: 192594 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0274. Min Act: -0.0003

Data Index: 940063 (C4 (Web Text))

Max Activating Token Index: 944

Text #18

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0262. Min Act: -0.0003

Data Index: 1476585 (Python Code)

Max Activating Token Index: 486

Text #19

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0268. Min Act: -0.0003

Data Index: 791149 (C4 (Web Text))

Max Activating Token Index: 551