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

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

Neuron 391 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: 0.0359. Min Range: -0.0359

Max Act: 0.0359. Min Act: -0.0006

Data Index: 95940 (C4 (Web Text))

Max Activating Token Index: 265

Text #1

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0336. Min Act: -0.0006

Data Index: 770751 (C4 (Web Text))

Max Activating Token Index: 455

Text #2

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0342. Min Act: -0.0006

Data Index: 448812 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0316. Min Act: -0.0006

Data Index: 773372 (C4 (Web Text))

Max Activating Token Index: 651

Text #4

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0302. Min Act: -0.0006

Data Index: 1088756 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0290. Min Act: -0.0006

Data Index: 1078656 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0298. Min Act: -0.0006

Data Index: 109511 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0280. Min Act: -0.0005

Data Index: 247421 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0274. Min Act: -0.0006

Data Index: 1246271 (C4 (Web Text))

Max Activating Token Index: 189

Text #9

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0272. Min Act: -0.0006

Data Index: 1051569 (C4 (Web Text))

Max Activating Token Index: 198

Text #10

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0263. Min Act: -0.0006

Data Index: 159654 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0257. Min Act: -0.0006

Data Index: 1033230 (C4 (Web Text))

Max Activating Token Index: 792

Text #12

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0263. Min Act: -0.0006

Data Index: 223985 (C4 (Web Text))

Max Activating Token Index: 152

Text #13

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0262. Min Act: -0.0006

Data Index: 455908 (C4 (Web Text))

Max Activating Token Index: 694

Text #14

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0254. Min Act: -0.0006

Data Index: 427814 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0260. Min Act: -0.0006

Data Index: 287365 (C4 (Web Text))

Max Activating Token Index: 756

Text #16

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0259. Min Act: -0.0006

Data Index: 42308 (C4 (Web Text))

Max Activating Token Index: 835

Text #17

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0253. Min Act: -0.0006

Data Index: 956271 (C4 (Web Text))

Max Activating Token Index: 818

Text #18

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0254. Min Act: -0.0006

Data Index: 42129 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0252. Min Act: -0.0006

Data Index: 145086 (C4 (Web Text))

Max Activating Token Index: 689