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

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

Neuron 4474 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: 0.0470. Min Range: -0.0470

Max Act: 0.0463. Min Act: -0.0002

Data Index: 1175061 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0470. Min Act: -0.0002

Data Index: 1119595 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0443. Min Act: -0.0002

Data Index: 1420338 (Python Code)

Max Activating Token Index: 443

Text #3

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0388. Min Act: -0.0002

Data Index: 1386414 (Python Code)

Max Activating Token Index: 299

Text #4

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0413. Min Act: -0.0002

Data Index: 1121362 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0397. Min Act: -0.0002

Data Index: 1563939 (Python Code)

Max Activating Token Index: 650

Text #6

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0377. Min Act: -0.0002

Data Index: 337338 (C4 (Web Text))

Max Activating Token Index: 97

Text #7

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0390. Min Act: -0.0002

Data Index: 498061 (C4 (Web Text))

Max Activating Token Index: 704

Text #8

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0339. Min Act: -0.0002

Data Index: 906241 (C4 (Web Text))

Max Activating Token Index: 670

Text #9

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0362. Min Act: -0.0002

Data Index: 27036 (C4 (Web Text))

Max Activating Token Index: 812

Text #10

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0369. Min Act: -0.0002

Data Index: 863486 (C4 (Web Text))

Max Activating Token Index: 644

Text #11

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0327. Min Act: -0.0002

Data Index: 1427540 (Python Code)

Max Activating Token Index: 949

Text #12

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0342. Min Act: -0.0002

Data Index: 838611 (C4 (Web Text))

Max Activating Token Index: 704

Text #13

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0334. Min Act: -0.0002

Data Index: 797443 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0353. Min Act: -0.0002

Data Index: 1116125 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0306. Min Act: -0.0002

Data Index: 307091 (C4 (Web Text))

Max Activating Token Index: 997

Text #16

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0318. Min Act: -0.0002

Data Index: 100414 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0341. Min Act: -0.0002

Data Index: 511403 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0330. Min Act: -0.0002

Data Index: 402204 (C4 (Web Text))

Max Activating Token Index: 374

Text #19

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0351. Min Act: -0.0002

Data Index: 172920 (C4 (Web Text))

Max Activating Token Index: 1008