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

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

Neuron 2447 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: 0.0567. Min Range: -0.0567

Max Act: 0.0567. Min Act: -0.0002

Data Index: 442676 (C4 (Web Text))

Max Activating Token Index: 942

Text #1

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0545. Min Act: -0.0002

Data Index: 1065159 (C4 (Web Text))

Max Activating Token Index: 373

Text #2

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0537. Min Act: -0.0002

Data Index: 1337995 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0415. Min Act: -0.0002

Data Index: 730282 (C4 (Web Text))

Max Activating Token Index: 532

Text #4

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0420. Min Act: -0.0002

Data Index: 571648 (C4 (Web Text))

Max Activating Token Index: 190

Text #5

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0421. Min Act: -0.0002

Data Index: 926408 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0421. Min Act: -0.0002

Data Index: 386053 (C4 (Web Text))

Max Activating Token Index: 412

Text #7

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0415. Min Act: -0.0002

Data Index: 1329943 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0401. Min Act: -0.0002

Data Index: 1159237 (C4 (Web Text))

Max Activating Token Index: 415

Text #9

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0428. Min Act: -0.0002

Data Index: 329398 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0409. Min Act: -0.0002

Data Index: 1275572 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0400. Min Act: -0.0002

Data Index: 673710 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0398. Min Act: -0.0002

Data Index: 563738 (C4 (Web Text))

Max Activating Token Index: 286

Text #13

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0403. Min Act: -0.0002

Data Index: 252538 (C4 (Web Text))

Max Activating Token Index: 130

Text #14

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0399. Min Act: -0.0002

Data Index: 57090 (C4 (Web Text))

Max Activating Token Index: 429

Text #15

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0383. Min Act: -0.0002

Data Index: 754572 (C4 (Web Text))

Max Activating Token Index: 609

Text #16

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0386. Min Act: -0.0002

Data Index: 26887 (C4 (Web Text))

Max Activating Token Index: 295

Text #17

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0386. Min Act: -0.0002

Data Index: 1108063 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0382. Min Act: -0.0002

Data Index: 1267862 (C4 (Web Text))

Max Activating Token Index: 485

Text #19

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0386. Min Act: -0.0002

Data Index: 1266472 (C4 (Web Text))

Max Activating Token Index: 971