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

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

Neuron 4845 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0532. Min Act: -0.0000

Data Index: 174652 (C4 (Web Text))

Max Activating Token Index: 169

Text #1

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0363. Min Act: -0.0000

Data Index: 779957 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0392. Min Act: -0.0000

Data Index: 30391 (C4 (Web Text))

Max Activating Token Index: 390

Text #3

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0448. Min Act: -0.0000

Data Index: 1058143 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0380. Min Act: -0.0000

Data Index: 280312 (C4 (Web Text))

Max Activating Token Index: 879

Text #5

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0350. Min Act: -0.0000

Data Index: 1129707 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0327. Min Act: -0.0000

Data Index: 1296156 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0353. Min Act: -0.0000

Data Index: 300001 (C4 (Web Text))

Max Activating Token Index: 195

Text #8

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0314. Min Act: -0.0000

Data Index: 440033 (C4 (Web Text))

Max Activating Token Index: 193

Text #9

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0338. Min Act: -0.0000

Data Index: 1042748 (C4 (Web Text))

Max Activating Token Index: 362

Text #10

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0305. Min Act: -0.0000

Data Index: 402828 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0302. Min Act: -0.0000

Data Index: 60508 (C4 (Web Text))

Max Activating Token Index: 71

Text #12

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0299. Min Act: -0.0000

Data Index: 1398618 (Python Code)

Max Activating Token Index: 411

Text #13

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0323. Min Act: -0.0000

Data Index: 1184382 (C4 (Web Text))

Max Activating Token Index: 443

Text #14

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0327. Min Act: -0.0000

Data Index: 522891 (C4 (Web Text))

Max Activating Token Index: 132

Text #15

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0304. Min Act: -0.0000

Data Index: 848759 (C4 (Web Text))

Max Activating Token Index: 432

Text #16

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0316. Min Act: -0.0000

Data Index: 331889 (C4 (Web Text))

Max Activating Token Index: 795

Text #17

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0317. Min Act: -0.0000

Data Index: 1090072 (C4 (Web Text))

Max Activating Token Index: 451

Text #18

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0298. Min Act: -0.0000

Data Index: 497457 (C4 (Web Text))

Max Activating Token Index: 976

Text #19

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0285. Min Act: -0.0000

Data Index: 168856 (C4 (Web Text))

Max Activating Token Index: 46