Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6091 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0485. Min Act: -0.0001

Data Index: 1064399 (C4 (Web Text))

Max Activating Token Index: 267

Text #1

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0344. Min Act: -0.0001

Data Index: 859502 (C4 (Web Text))

Max Activating Token Index: 748

Text #2

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0314. Min Act: -0.0001

Data Index: 254706 (C4 (Web Text))

Max Activating Token Index: 700

Text #3

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0328. Min Act: -0.0001

Data Index: 1102833 (C4 (Web Text))

Max Activating Token Index: 371

Text #4

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0328. Min Act: -0.0001

Data Index: 469363 (C4 (Web Text))

Max Activating Token Index: 313

Text #5

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0301. Min Act: -0.0001

Data Index: 906998 (C4 (Web Text))

Max Activating Token Index: 373

Text #6

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0314. Min Act: -0.0001

Data Index: 330161 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0309. Min Act: -0.0001

Data Index: 521570 (C4 (Web Text))

Max Activating Token Index: 566

Text #8

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0294. Min Act: -0.0001

Data Index: 476977 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0299. Min Act: -0.0002

Data Index: 900230 (C4 (Web Text))

Max Activating Token Index: 807

Text #10

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0314. Min Act: -0.0001

Data Index: 670985 (C4 (Web Text))

Max Activating Token Index: 358

Text #11

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0295. Min Act: -0.0001

Data Index: 810087 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0297. Min Act: -0.0001

Data Index: 742282 (C4 (Web Text))

Max Activating Token Index: 855

Text #13

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0271. Min Act: -0.0001

Data Index: 589676 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0276. Min Act: -0.0001

Data Index: 1152062 (C4 (Web Text))

Max Activating Token Index: 926

Text #15

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0283. Min Act: -0.0001

Data Index: 1236657 (C4 (Web Text))

Max Activating Token Index: 248

Text #16

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0287. Min Act: -0.0001

Data Index: 965888 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0284. Min Act: -0.0001

Data Index: 911360 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0253. Min Act: -0.0001

Data Index: 713261 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0274. Min Act: -0.0001

Data Index: 3519 (C4 (Web Text))

Max Activating Token Index: 429