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

Dataset: The Pile

Neuron 3067 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.7421. Min Range: -7.7421

Max Act: 7.7421. Min Act: 0.0000

Data Index: 815335 (The Pile)

Max Activating Token Index: 530

Text #1

Max Range: 7.7421. Min Range: -7.7421

Max Act: 7.3070. Min Act: -0.0000

Data Index: 971971 (The Pile)

Max Activating Token Index: 814

Text #2

Max Range: 7.7421. Min Range: -7.7421

Max Act: 7.2584. Min Act: -0.0000

Data Index: 947372 (The Pile)

Max Activating Token Index: 667

Text #3

Max Range: 7.7421. Min Range: -7.7421

Max Act: 7.1264. Min Act: -0.0000

Data Index: 958165 (The Pile)

Max Activating Token Index: 967

Text #4

Max Range: 7.7421. Min Range: -7.7421

Max Act: 6.8937. Min Act: -0.0000

Data Index: 1547937 (The Pile)

Max Activating Token Index: 111

Text #5

Max Range: 7.7421. Min Range: -7.7421

Max Act: 6.9880. Min Act: -0.0000

Data Index: 456540 (The Pile)

Max Activating Token Index: 712

Text #6

Max Range: 7.7421. Min Range: -7.7421

Max Act: 7.1386. Min Act: -0.0000

Data Index: 862515 (The Pile)

Max Activating Token Index: 351

Text #7

Max Range: 7.7421. Min Range: -7.7421

Max Act: 6.6301. Min Act: -0.0000

Data Index: 322322 (The Pile)

Max Activating Token Index: 627

Text #8

Max Range: 7.7421. Min Range: -7.7421

Max Act: 6.7358. Min Act: 0.0000

Data Index: 1620074 (The Pile)

Max Activating Token Index: 151

Text #9

Max Range: 7.7421. Min Range: -7.7421

Max Act: 6.7261. Min Act: -0.0000

Data Index: 653433 (The Pile)

Max Activating Token Index: 411

Text #10

Max Range: 7.7421. Min Range: -7.7421

Max Act: 6.7109. Min Act: -0.0000

Data Index: 959713 (The Pile)

Max Activating Token Index: 384

Text #11

Max Range: 7.7421. Min Range: -7.7421

Max Act: 6.6059. Min Act: 0.0000

Data Index: 706941 (The Pile)

Max Activating Token Index: 917

Text #12

Max Range: 7.7421. Min Range: -7.7421

Max Act: 6.9545. Min Act: -0.0000

Data Index: 1585107 (The Pile)

Max Activating Token Index: 677

Text #13

Max Range: 7.7421. Min Range: -7.7421

Max Act: 6.5533. Min Act: -0.0000

Data Index: 258799 (The Pile)

Max Activating Token Index: 380

Text #14

Max Range: 7.7421. Min Range: -7.7421

Max Act: 6.3362. Min Act: -0.0000

Data Index: 444295 (The Pile)

Max Activating Token Index: 941

Text #15

Max Range: 7.7421. Min Range: -7.7421

Max Act: 6.6956. Min Act: 0.0000

Data Index: 1244654 (The Pile)

Max Activating Token Index: 451

Text #16

Max Range: 7.7421. Min Range: -7.7421

Max Act: 6.4341. Min Act: -0.0000

Data Index: 821461 (The Pile)

Max Activating Token Index: 171

Text #17

Max Range: 7.7421. Min Range: -7.7421

Max Act: 6.4503. Min Act: -0.0000

Data Index: 911034 (The Pile)

Max Activating Token Index: 754

Text #18

Max Range: 7.7421. Min Range: -7.7421

Max Act: 6.4377. Min Act: -0.0000

Data Index: 1421284 (The Pile)

Max Activating Token Index: 296

Text #19

Max Range: 7.7421. Min Range: -7.7421

Max Act: 6.1571. Min Act: -0.0000

Data Index: 80872 (The Pile)

Max Activating Token Index: 499