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

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

Neuron 725 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0363. Min Act: -0.0002

Data Index: 898007 (C4 (Web Text))

Max Activating Token Index: 516

Text #1

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0347. Min Act: -0.0002

Data Index: 407844 (C4 (Web Text))

Max Activating Token Index: 624

Text #2

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0296. Min Act: -0.0002

Data Index: 715628 (C4 (Web Text))

Max Activating Token Index: 199

Text #3

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0298. Min Act: -0.0002

Data Index: 893118 (C4 (Web Text))

Max Activating Token Index: 371

Text #4

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0290. Min Act: -0.0002

Data Index: 559608 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0288. Min Act: -0.0002

Data Index: 35482 (C4 (Web Text))

Max Activating Token Index: 231

Text #6

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0226. Min Act: -0.0002

Data Index: 1334104 (C4 (Web Text))

Max Activating Token Index: 147

Text #7

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0290. Min Act: -0.0002

Data Index: 1273320 (C4 (Web Text))

Max Activating Token Index: 953

Text #8

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0250. Min Act: -0.0002

Data Index: 498912 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0267. Min Act: -0.0002

Data Index: 946479 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0279. Min Act: -0.0002

Data Index: 1318540 (C4 (Web Text))

Max Activating Token Index: 1022

Text #11

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0260. Min Act: -0.0002

Data Index: 1180572 (C4 (Web Text))

Max Activating Token Index: 595

Text #12

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0269. Min Act: -0.0002

Data Index: 383797 (C4 (Web Text))

Max Activating Token Index: 980

Text #13

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0272. Min Act: -0.0002

Data Index: 494343 (C4 (Web Text))

Max Activating Token Index: 591

Text #14

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0281. Min Act: -0.0002

Data Index: 328548 (C4 (Web Text))

Max Activating Token Index: 345

Text #15

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0263. Min Act: -0.0002

Data Index: 49818 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0236. Min Act: -0.0002

Data Index: 982708 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0269. Min Act: -0.0002

Data Index: 651656 (C4 (Web Text))

Max Activating Token Index: 148

Text #18

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0247. Min Act: -0.0002

Data Index: 676135 (C4 (Web Text))

Max Activating Token Index: 927

Text #19

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0245. Min Act: -0.0002

Data Index: 350452 (C4 (Web Text))

Max Activating Token Index: 265