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

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

Neuron 3777 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.4580. Min Act: -0.0000

Data Index: 41718 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.4447. Min Act: -0.0000

Data Index: 282093 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.4172. Min Act: -0.0000

Data Index: 199319 (C4 (Web Text))

Max Activating Token Index: 513

Text #3

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.3885. Min Act: -0.0000

Data Index: 491860 (C4 (Web Text))

Max Activating Token Index: 431

Text #4

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.3356. Min Act: -0.0000

Data Index: 259705 (C4 (Web Text))

Max Activating Token Index: 867

Text #5

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.3532. Min Act: -0.0000

Data Index: 845184 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.3358. Min Act: -0.0000

Data Index: 881011 (C4 (Web Text))

Max Activating Token Index: 332

Text #7

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.3230. Min Act: -0.0000

Data Index: 358219 (C4 (Web Text))

Max Activating Token Index: 113

Text #8

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.3325. Min Act: -0.0000

Data Index: 736709 (C4 (Web Text))

Max Activating Token Index: 308

Text #9

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.3279. Min Act: -0.0000

Data Index: 42550 (C4 (Web Text))

Max Activating Token Index: 574

Text #10

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.3170. Min Act: -0.0000

Data Index: 515228 (C4 (Web Text))

Max Activating Token Index: 828

Text #11

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.3162. Min Act: -0.0000

Data Index: 1143181 (C4 (Web Text))

Max Activating Token Index: 893

Text #12

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.3350. Min Act: -0.0000

Data Index: 658670 (C4 (Web Text))

Max Activating Token Index: 509

Text #13

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.3132. Min Act: -0.0000

Data Index: 87418 (C4 (Web Text))

Max Activating Token Index: 396

Text #14

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.3159. Min Act: -0.0000

Data Index: 912156 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.2717. Min Act: -0.0000

Data Index: 976999 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.2925. Min Act: -0.0000

Data Index: 376915 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.2994. Min Act: -0.0000

Data Index: 227434 (C4 (Web Text))

Max Activating Token Index: 782

Text #18

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.3077. Min Act: -0.0000

Data Index: 655514 (C4 (Web Text))

Max Activating Token Index: 183

Text #19

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.2970. Min Act: -0.0000

Data Index: 676931 (C4 (Web Text))

Max Activating Token Index: 649