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

Dataset: The Pile

Neuron 1065 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4108. Min Range: -0.4108

Max Act: 0.4108. Min Act: -0.0000

Data Index: 1002608 (The Pile)

Max Activating Token Index: 944

Text #1

Max Range: 0.4108. Min Range: -0.4108

Max Act: 0.3119. Min Act: -0.0000

Data Index: 147688 (The Pile)

Max Activating Token Index: 986

Text #2

Max Range: 0.4108. Min Range: -0.4108

Max Act: 0.3083. Min Act: -0.0000

Data Index: 1456621 (The Pile)

Max Activating Token Index: 862

Text #3

Max Range: 0.4108. Min Range: -0.4108

Max Act: 0.2918. Min Act: -0.0000

Data Index: 422420 (The Pile)

Max Activating Token Index: 335

Text #4

Max Range: 0.4108. Min Range: -0.4108

Max Act: 0.3241. Min Act: -0.0000

Data Index: 1903802 (The Pile)

Max Activating Token Index: 474

Text #5

Max Range: 0.4108. Min Range: -0.4108

Max Act: 0.2584. Min Act: -0.0000

Data Index: 1682088 (The Pile)

Max Activating Token Index: 446

Text #6

Max Range: 0.4108. Min Range: -0.4108

Max Act: 0.2409. Min Act: -0.0000

Data Index: 426655 (The Pile)

Max Activating Token Index: 173

Text #7

Max Range: 0.4108. Min Range: -0.4108

Max Act: 0.2383. Min Act: -0.0000

Data Index: 1121043 (The Pile)

Max Activating Token Index: 849

Text #8

Max Range: 0.4108. Min Range: -0.4108

Max Act: 0.2220. Min Act: -0.0000

Data Index: 563891 (The Pile)

Max Activating Token Index: 738

Text #9

Max Range: 0.4108. Min Range: -0.4108

Max Act: 0.2454. Min Act: -0.0000

Data Index: 539756 (The Pile)

Max Activating Token Index: 916

Text #10

Max Range: 0.4108. Min Range: -0.4108

Max Act: 0.2196. Min Act: -0.0000

Data Index: 294180 (The Pile)

Max Activating Token Index: 579

Text #11

Max Range: 0.4108. Min Range: -0.4108

Max Act: 0.2312. Min Act: -0.0000

Data Index: 323382 (The Pile)

Max Activating Token Index: 145

Text #12

Max Range: 0.4108. Min Range: -0.4108

Max Act: 0.2469. Min Act: -0.0000

Data Index: 1198997 (The Pile)

Max Activating Token Index: 295

Text #13

Max Range: 0.4108. Min Range: -0.4108

Max Act: 0.2616. Min Act: -0.0000

Data Index: 364720 (The Pile)

Max Activating Token Index: 458

Text #14

Max Range: 0.4108. Min Range: -0.4108

Max Act: 0.2348. Min Act: -0.0000

Data Index: 539592 (The Pile)

Max Activating Token Index: 565

Text #15

Max Range: 0.4108. Min Range: -0.4108

Max Act: 0.2306. Min Act: -0.0000

Data Index: 1969433 (The Pile)

Max Activating Token Index: 335

Text #16

Max Range: 0.4108. Min Range: -0.4108

Max Act: 0.2407. Min Act: -0.0000

Data Index: 1861517 (The Pile)

Max Activating Token Index: 251

Text #17

Max Range: 0.4108. Min Range: -0.4108

Max Act: 0.2193. Min Act: -0.0000

Data Index: 1442204 (The Pile)

Max Activating Token Index: 724

Text #18

Max Range: 0.4108. Min Range: -0.4108

Max Act: 0.2092. Min Act: -0.0000

Data Index: 892210 (The Pile)

Max Activating Token Index: 867

Text #19

Max Range: 0.4108. Min Range: -0.4108

Max Act: 0.2196. Min Act: -0.0000

Data Index: 1548964 (The Pile)

Max Activating Token Index: 630