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

Dataset: The Pile

Neuron 4134 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7336. Min Range: -3.7336

Max Act: 3.7336. Min Act: -0.0000

Data Index: 380134 (The Pile)

Max Activating Token Index: 467

Text #1

Max Range: 3.7336. Min Range: -3.7336

Max Act: 3.1689. Min Act: -0.0000

Data Index: 1585505 (The Pile)

Max Activating Token Index: 935

Text #2

Max Range: 3.7336. Min Range: -3.7336

Max Act: 3.4820. Min Act: -0.0000

Data Index: 1461292 (The Pile)

Max Activating Token Index: 194

Text #3

Max Range: 3.7336. Min Range: -3.7336

Max Act: 3.2211. Min Act: -0.0000

Data Index: 817724 (The Pile)

Max Activating Token Index: 49

Text #4

Max Range: 3.7336. Min Range: -3.7336

Max Act: 3.2697. Min Act: -0.0000

Data Index: 1362738 (The Pile)

Max Activating Token Index: 777

Text #5

Max Range: 3.7336. Min Range: -3.7336

Max Act: 2.8034. Min Act: -0.0000

Data Index: 92191 (The Pile)

Max Activating Token Index: 983

Text #6

Max Range: 3.7336. Min Range: -3.7336

Max Act: 3.3173. Min Act: -0.0000

Data Index: 1213351 (The Pile)

Max Activating Token Index: 1021

Text #7

Max Range: 3.7336. Min Range: -3.7336

Max Act: 2.9999. Min Act: -0.0000

Data Index: 634910 (The Pile)

Max Activating Token Index: 201

Text #8

Max Range: 3.7336. Min Range: -3.7336

Max Act: 3.1381. Min Act: -0.0000

Data Index: 488834 (The Pile)

Max Activating Token Index: 645

Text #9

Max Range: 3.7336. Min Range: -3.7336

Max Act: 3.1327. Min Act: -0.0000

Data Index: 1853520 (The Pile)

Max Activating Token Index: 264

Text #10

Max Range: 3.7336. Min Range: -3.7336

Max Act: 3.1164. Min Act: -0.0000

Data Index: 1572554 (The Pile)

Max Activating Token Index: 160

Text #11

Max Range: 3.7336. Min Range: -3.7336

Max Act: 3.2404. Min Act: -0.0000

Data Index: 292872 (The Pile)

Max Activating Token Index: 50

Text #12

Max Range: 3.7336. Min Range: -3.7336

Max Act: 2.9584. Min Act: -0.0000

Data Index: 415905 (The Pile)

Max Activating Token Index: 696

Text #13

Max Range: 3.7336. Min Range: -3.7336

Max Act: 3.0734. Min Act: -0.0000

Data Index: 598359 (The Pile)

Max Activating Token Index: 47

Text #14

Max Range: 3.7336. Min Range: -3.7336

Max Act: 2.9179. Min Act: -0.0000

Data Index: 1914228 (The Pile)

Max Activating Token Index: 962

Text #15

Max Range: 3.7336. Min Range: -3.7336

Max Act: 2.9223. Min Act: -0.0000

Data Index: 180051 (The Pile)

Max Activating Token Index: 887

Text #16

Max Range: 3.7336. Min Range: -3.7336

Max Act: 2.9792. Min Act: -0.0000

Data Index: 886085 (The Pile)

Max Activating Token Index: 847

Text #17

Max Range: 3.7336. Min Range: -3.7336

Max Act: 2.9629. Min Act: -0.0000

Data Index: 1424111 (The Pile)

Max Activating Token Index: 369

Text #18

Max Range: 3.7336. Min Range: -3.7336

Max Act: 2.7939. Min Act: -0.0000

Data Index: 976091 (The Pile)

Max Activating Token Index: 433

Text #19

Max Range: 3.7336. Min Range: -3.7336

Max Act: 2.7989. Min Act: -0.0000

Data Index: 1486519 (The Pile)

Max Activating Token Index: 368