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

Dataset: The Pile

Neuron 1004 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.4282. Min Act: -0.0000

Data Index: 1242298 (The Pile)

Max Activating Token Index: 603

Text #1

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3713. Min Act: -0.0000

Data Index: 673346 (The Pile)

Max Activating Token Index: 703

Text #2

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3553. Min Act: -0.0000

Data Index: 542158 (The Pile)

Max Activating Token Index: 743

Text #3

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3507. Min Act: -0.0000

Data Index: 1275878 (The Pile)

Max Activating Token Index: 599

Text #4

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3290. Min Act: -0.0000

Data Index: 1275549 (The Pile)

Max Activating Token Index: 886

Text #5

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3523. Min Act: -0.0000

Data Index: 1616618 (The Pile)

Max Activating Token Index: 353

Text #6

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3202. Min Act: -0.0000

Data Index: 163005 (The Pile)

Max Activating Token Index: 1018

Text #7

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3368. Min Act: -0.0000

Data Index: 874357 (The Pile)

Max Activating Token Index: 247

Text #8

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3484. Min Act: -0.0000

Data Index: 975157 (The Pile)

Max Activating Token Index: 182

Text #9

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3560. Min Act: -0.0000

Data Index: 1401298 (The Pile)

Max Activating Token Index: 1018

Text #10

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3171. Min Act: -0.0000

Data Index: 1079366 (The Pile)

Max Activating Token Index: 173

Text #11

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3252. Min Act: -0.0000

Data Index: 798156 (The Pile)

Max Activating Token Index: 57

Text #12

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3198. Min Act: -0.0000

Data Index: 1961654 (The Pile)

Max Activating Token Index: 935

Text #13

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3134. Min Act: -0.0000

Data Index: 1221382 (The Pile)

Max Activating Token Index: 341

Text #14

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3024. Min Act: -0.0000

Data Index: 576346 (The Pile)

Max Activating Token Index: 251

Text #15

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3173. Min Act: -0.0000

Data Index: 1933117 (The Pile)

Max Activating Token Index: 709

Text #16

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3204. Min Act: -0.0000

Data Index: 1145167 (The Pile)

Max Activating Token Index: 580

Text #17

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3080. Min Act: -0.0000

Data Index: 1843837 (The Pile)

Max Activating Token Index: 776

Text #18

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.2990. Min Act: -0.0000

Data Index: 1770024 (The Pile)

Max Activating Token Index: 29

Text #19

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.2783. Min Act: -0.0000

Data Index: 1127013 (The Pile)

Max Activating Token Index: 672