Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3631 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.6026. Min Range: -1.6026

Max Act: 1.6026. Min Act: -0.0000

Data Index: 1417721 (The Pile)

Max Activating Token Index: 705

Text #1

Max Range: 1.6026. Min Range: -1.6026

Max Act: 1.4429. Min Act: -0.0000

Data Index: 587995 (The Pile)

Max Activating Token Index: 59

Text #2

Max Range: 1.6026. Min Range: -1.6026

Max Act: 1.2784. Min Act: -0.0000

Data Index: 555656 (The Pile)

Max Activating Token Index: 177

Text #3

Max Range: 1.6026. Min Range: -1.6026

Max Act: 1.3175. Min Act: -0.0000

Data Index: 1156136 (The Pile)

Max Activating Token Index: 765

Text #4

Max Range: 1.6026. Min Range: -1.6026

Max Act: 1.3140. Min Act: -0.0000

Data Index: 1147048 (The Pile)

Max Activating Token Index: 1004

Text #5

Max Range: 1.6026. Min Range: -1.6026

Max Act: 1.2866. Min Act: -0.0000

Data Index: 1976422 (The Pile)

Max Activating Token Index: 834

Text #6

Max Range: 1.6026. Min Range: -1.6026

Max Act: 1.3319. Min Act: -0.0000

Data Index: 318445 (The Pile)

Max Activating Token Index: 679

Text #7

Max Range: 1.6026. Min Range: -1.6026

Max Act: 1.2330. Min Act: -0.0000

Data Index: 572103 (The Pile)

Max Activating Token Index: 198

Text #8

Max Range: 1.6026. Min Range: -1.6026

Max Act: 1.2607. Min Act: -0.0000

Data Index: 1252199 (The Pile)

Max Activating Token Index: 611

Text #9

Max Range: 1.6026. Min Range: -1.6026

Max Act: 1.2150. Min Act: -0.0000

Data Index: 1647079 (The Pile)

Max Activating Token Index: 164

Text #10

Max Range: 1.6026. Min Range: -1.6026

Max Act: 1.2069. Min Act: -0.0000

Data Index: 1139433 (The Pile)

Max Activating Token Index: 973

Text #11

Max Range: 1.6026. Min Range: -1.6026

Max Act: 1.2819. Min Act: -0.0000

Data Index: 606731 (The Pile)

Max Activating Token Index: 934

Text #12

Max Range: 1.6026. Min Range: -1.6026

Max Act: 1.2042. Min Act: -0.0000

Data Index: 1290315 (The Pile)

Max Activating Token Index: 136

Text #13

Max Range: 1.6026. Min Range: -1.6026

Max Act: 1.1881. Min Act: -0.0000

Data Index: 179364 (The Pile)

Max Activating Token Index: 434

Text #14

Max Range: 1.6026. Min Range: -1.6026

Max Act: 1.2178. Min Act: -0.0000

Data Index: 1545426 (The Pile)

Max Activating Token Index: 210

Text #15

Max Range: 1.6026. Min Range: -1.6026

Max Act: 1.1579. Min Act: -0.0000

Data Index: 716737 (The Pile)

Max Activating Token Index: 744

Text #16

Max Range: 1.6026. Min Range: -1.6026

Max Act: 1.0914. Min Act: -0.0000

Data Index: 1447666 (The Pile)

Max Activating Token Index: 948

Text #17

Max Range: 1.6026. Min Range: -1.6026

Max Act: 1.1897. Min Act: -0.0000

Data Index: 1008477 (The Pile)

Max Activating Token Index: 767

Text #18

Max Range: 1.6026. Min Range: -1.6026

Max Act: 1.1563. Min Act: -0.0000

Data Index: 641343 (The Pile)

Max Activating Token Index: 992

Text #19

Max Range: 1.6026. Min Range: -1.6026

Max Act: 1.1533. Min Act: -0.0000

Data Index: 1491842 (The Pile)

Max Activating Token Index: 421