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

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

Neuron 3141 in Layer 2

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: -0.0002

Data Index: 44412 (C4 (Web Text))

Max Activating Token Index: 476

Text #1

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0473. Min Act: -0.0002

Data Index: 4848 (C4 (Web Text))

Max Activating Token Index: 322

Text #2

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0402. Min Act: -0.0002

Data Index: 319320 (C4 (Web Text))

Max Activating Token Index: 412

Text #3

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0357. Min Act: -0.0002

Data Index: 365177 (C4 (Web Text))

Max Activating Token Index: 639

Text #4

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0353. Min Act: -0.0002

Data Index: 527655 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0338. Min Act: -0.0002

Data Index: 248281 (C4 (Web Text))

Max Activating Token Index: 589

Text #6

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0339. Min Act: -0.0002

Data Index: 335810 (C4 (Web Text))

Max Activating Token Index: 448

Text #7

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0333. Min Act: -0.0002

Data Index: 1117465 (C4 (Web Text))

Max Activating Token Index: 851

Text #8

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0347. Min Act: -0.0002

Data Index: 217678 (C4 (Web Text))

Max Activating Token Index: 836

Text #9

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0326. Min Act: -0.0002

Data Index: 188747 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0321. Min Act: -0.0002

Data Index: 1111534 (C4 (Web Text))

Max Activating Token Index: 513

Text #11

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0329. Min Act: -0.0002

Data Index: 1217717 (C4 (Web Text))

Max Activating Token Index: 840

Text #12

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0328. Min Act: -0.0002

Data Index: 881886 (C4 (Web Text))

Max Activating Token Index: 63

Text #13

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0321. Min Act: -0.0002

Data Index: 480648 (C4 (Web Text))

Max Activating Token Index: 397

Text #14

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0323. Min Act: -0.0002

Data Index: 1102613 (C4 (Web Text))

Max Activating Token Index: 585

Text #15

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0318. Min Act: -0.0002

Data Index: 822184 (C4 (Web Text))

Max Activating Token Index: 890

Text #16

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0312. Min Act: -0.0002

Data Index: 472529 (C4 (Web Text))

Max Activating Token Index: 914

Text #17

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0304. Min Act: -0.0002

Data Index: 605390 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0308. Min Act: -0.0002

Data Index: 116250 (C4 (Web Text))

Max Activating Token Index: 197

Text #19

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0315. Min Act: -0.0002

Data Index: 168502 (C4 (Web Text))

Max Activating Token Index: 725