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

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

Neuron 2458 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4173. Min Range: -0.4173

Max Act: 0.4173. Min Act: -0.0000

Data Index: 1150200 (C4 (Web Text))

Max Activating Token Index: 325

Text #1

Max Range: 0.4173. Min Range: -0.4173

Max Act: 0.4099. Min Act: -0.0000

Data Index: 1116444 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 0.4173. Min Range: -0.4173

Max Act: 0.4133. Min Act: -0.0000

Data Index: 1234190 (C4 (Web Text))

Max Activating Token Index: 150

Text #3

Max Range: 0.4173. Min Range: -0.4173

Max Act: 0.3831. Min Act: -0.0000

Data Index: 1079709 (C4 (Web Text))

Max Activating Token Index: 253

Text #4

Max Range: 0.4173. Min Range: -0.4173

Max Act: 0.3471. Min Act: -0.0000

Data Index: 214198 (C4 (Web Text))

Max Activating Token Index: 465

Text #5

Max Range: 0.4173. Min Range: -0.4173

Max Act: 0.3232. Min Act: -0.0000

Data Index: 645563 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 0.4173. Min Range: -0.4173

Max Act: 0.3226. Min Act: -0.0000

Data Index: 457939 (C4 (Web Text))

Max Activating Token Index: 687

Text #7

Max Range: 0.4173. Min Range: -0.4173

Max Act: 0.3235. Min Act: -0.0000

Data Index: 988434 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 0.4173. Min Range: -0.4173

Max Act: 0.3585. Min Act: -0.0000

Data Index: 1175778 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 0.4173. Min Range: -0.4173

Max Act: 0.3359. Min Act: -0.0000

Data Index: 396471 (C4 (Web Text))

Max Activating Token Index: 681

Text #10

Max Range: 0.4173. Min Range: -0.4173

Max Act: 0.3336. Min Act: -0.0000

Data Index: 75081 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 0.4173. Min Range: -0.4173

Max Act: 0.3425. Min Act: -0.0000

Data Index: 619661 (C4 (Web Text))

Max Activating Token Index: 827

Text #12

Max Range: 0.4173. Min Range: -0.4173

Max Act: 0.3297. Min Act: -0.0000

Data Index: 1078128 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 0.4173. Min Range: -0.4173

Max Act: 0.3405. Min Act: -0.0000

Data Index: 329339 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 0.4173. Min Range: -0.4173

Max Act: 0.3416. Min Act: -0.0000

Data Index: 613492 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 0.4173. Min Range: -0.4173

Max Act: 0.3277. Min Act: -0.0000

Data Index: 104100 (C4 (Web Text))

Max Activating Token Index: 4

Text #16

Max Range: 0.4173. Min Range: -0.4173

Max Act: 0.3249. Min Act: -0.0000

Data Index: 342187 (C4 (Web Text))

Max Activating Token Index: 941

Text #17

Max Range: 0.4173. Min Range: -0.4173

Max Act: 0.3479. Min Act: -0.0000

Data Index: 459502 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 0.4173. Min Range: -0.4173

Max Act: 0.3103. Min Act: -0.0000

Data Index: 19327 (C4 (Web Text))

Max Activating Token Index: 596

Text #19

Max Range: 0.4173. Min Range: -0.4173

Max Act: 0.3304. Min Act: -0.0000

Data Index: 837571 (C4 (Web Text))

Max Activating Token Index: 21