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

Dataset: The Pile

Neuron 993 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.4568. Min Act: -0.0000

Data Index: 1387743 (The Pile)

Max Activating Token Index: 747

Text #1

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.4466. Min Act: -0.0000

Data Index: 1464197 (The Pile)

Max Activating Token Index: 292

Text #2

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.3392. Min Act: -0.0000

Data Index: 1556340 (The Pile)

Max Activating Token Index: 419

Text #3

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.2140. Min Act: -0.0000

Data Index: 1816044 (The Pile)

Max Activating Token Index: 832

Text #4

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.1134. Min Act: -0.0000

Data Index: 1773494 (The Pile)

Max Activating Token Index: 72

Text #5

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.2194. Min Act: -0.0000

Data Index: 680097 (The Pile)

Max Activating Token Index: 569

Text #6

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.2050. Min Act: -0.0000

Data Index: 659354 (The Pile)

Max Activating Token Index: 860

Text #7

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.1238. Min Act: -0.0000

Data Index: 1196433 (The Pile)

Max Activating Token Index: 862

Text #8

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.0288. Min Act: -0.0000

Data Index: 1842792 (The Pile)

Max Activating Token Index: 53

Text #9

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.0560. Min Act: -0.0000

Data Index: 1065453 (The Pile)

Max Activating Token Index: 189

Text #10

Max Range: 1.4568. Min Range: -1.4568

Max Act: 0.9443. Min Act: -0.0000

Data Index: 281006 (The Pile)

Max Activating Token Index: 875

Text #11

Max Range: 1.4568. Min Range: -1.4568

Max Act: 0.9159. Min Act: -0.0000

Data Index: 145614 (The Pile)

Max Activating Token Index: 237

Text #12

Max Range: 1.4568. Min Range: -1.4568

Max Act: 0.9317. Min Act: -0.0000

Data Index: 1137516 (The Pile)

Max Activating Token Index: 182

Text #13

Max Range: 1.4568. Min Range: -1.4568

Max Act: 0.9397. Min Act: -0.0000

Data Index: 1371832 (The Pile)

Max Activating Token Index: 539

Text #14

Max Range: 1.4568. Min Range: -1.4568

Max Act: 0.9041. Min Act: -0.0000

Data Index: 739566 (The Pile)

Max Activating Token Index: 157

Text #15

Max Range: 1.4568. Min Range: -1.4568

Max Act: 0.8333. Min Act: -0.0000

Data Index: 1206825 (The Pile)

Max Activating Token Index: 449

Text #16

Max Range: 1.4568. Min Range: -1.4568

Max Act: 0.8131. Min Act: -0.0000

Data Index: 544986 (The Pile)

Max Activating Token Index: 923

Text #17

Max Range: 1.4568. Min Range: -1.4568

Max Act: 0.8844. Min Act: -0.0000

Data Index: 213779 (The Pile)

Max Activating Token Index: 568

Text #18

Max Range: 1.4568. Min Range: -1.4568

Max Act: 0.8376. Min Act: -0.0000

Data Index: 1065199 (The Pile)

Max Activating Token Index: 989

Text #19

Max Range: 1.4568. Min Range: -1.4568

Max Act: 0.8667. Min Act: -0.0000

Data Index: 808390 (The Pile)

Max Activating Token Index: 75