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

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

Neuron 2374 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0365. Min Act: -0.0002

Data Index: 1010369 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0369. Min Act: -0.0002

Data Index: 493729 (C4 (Web Text))

Max Activating Token Index: 857

Text #2

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0466. Min Act: -0.0002

Data Index: 1122903 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0445. Min Act: -0.0002

Data Index: 169098 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0464. Min Act: -0.0002

Data Index: 86582 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0394. Min Act: -0.0002

Data Index: 43597 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0381. Min Act: -0.0002

Data Index: 1201705 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0430. Min Act: -0.0002

Data Index: 798647 (C4 (Web Text))

Max Activating Token Index: 195

Text #8

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0417. Min Act: -0.0002

Data Index: 1053659 (C4 (Web Text))

Max Activating Token Index: 826

Text #9

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0319. Min Act: -0.0002

Data Index: 1063293 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0405. Min Act: -0.0002

Data Index: 416976 (C4 (Web Text))

Max Activating Token Index: 520

Text #11

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0350. Min Act: -0.0002

Data Index: 1108584 (C4 (Web Text))

Max Activating Token Index: 417

Text #12

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0409. Min Act: -0.0002

Data Index: 220737 (C4 (Web Text))

Max Activating Token Index: 763

Text #13

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0457. Min Act: -0.0002

Data Index: 521165 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0439. Min Act: -0.0002

Data Index: 261422 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0350. Min Act: -0.0002

Data Index: 1463330 (Python Code)

Max Activating Token Index: 360

Text #16

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0387. Min Act: -0.0002

Data Index: 267774 (C4 (Web Text))

Max Activating Token Index: 973

Text #17

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0387. Min Act: -0.0002

Data Index: 1207142 (C4 (Web Text))

Max Activating Token Index: 15

Text #18

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0299. Min Act: -0.0002

Data Index: 667884 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0417. Min Act: -0.0002

Data Index: 1298571 (C4 (Web Text))

Max Activating Token Index: 950