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

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

Neuron 1652 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.4418. Min Act: -0.0000

Data Index: 1200193 (C4 (Web Text))

Max Activating Token Index: 835

Text #1

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.4127. Min Act: 0.0000

Data Index: 430462 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.3999. Min Act: -0.0000

Data Index: 719432 (C4 (Web Text))

Max Activating Token Index: 572

Text #3

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.3666. Min Act: -0.0000

Data Index: 377161 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.3711. Min Act: -0.0000

Data Index: 702570 (C4 (Web Text))

Max Activating Token Index: 231

Text #5

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.3608. Min Act: -0.0000

Data Index: 739654 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.3627. Min Act: -0.0000

Data Index: 384243 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.3436. Min Act: -0.0000

Data Index: 577448 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.3409. Min Act: -0.0000

Data Index: 848429 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.3396. Min Act: -0.0000

Data Index: 1181552 (C4 (Web Text))

Max Activating Token Index: 441

Text #10

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.3362. Min Act: -0.0000

Data Index: 1140696 (C4 (Web Text))

Max Activating Token Index: 452

Text #11

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.3353. Min Act: -0.0000

Data Index: 1108732 (C4 (Web Text))

Max Activating Token Index: 592

Text #12

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.3237. Min Act: -0.0000

Data Index: 26836 (C4 (Web Text))

Max Activating Token Index: 671

Text #13

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.3480. Min Act: 0.0000

Data Index: 1584505 (Python Code)

Max Activating Token Index: 288

Text #14

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.3324. Min Act: -0.0000

Data Index: 653969 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.3391. Min Act: -0.0000

Data Index: 84977 (C4 (Web Text))

Max Activating Token Index: 156

Text #16

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.3253. Min Act: -0.0000

Data Index: 69006 (C4 (Web Text))

Max Activating Token Index: 548

Text #17

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.3248. Min Act: -0.0000

Data Index: 1042047 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.3209. Min Act: -0.0000

Data Index: 637874 (C4 (Web Text))

Max Activating Token Index: 177

Text #19

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.3341. Min Act: -0.0000

Data Index: 1244737 (C4 (Web Text))

Max Activating Token Index: 679