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

Dataset: The Pile

Neuron 3028 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: 1.3530. Min Range: -1.3530

Max Act: 1.2857. Min Act: -0.0000

Data Index: 1905539 (The Pile)

Max Activating Token Index: 114

Text #1

Max Range: 1.3530. Min Range: -1.3530

Max Act: 1.3530. Min Act: -0.0000

Data Index: 949072 (The Pile)

Max Activating Token Index: 189

Text #2

Max Range: 1.3530. Min Range: -1.3530

Max Act: 1.2259. Min Act: -0.0000

Data Index: 705743 (The Pile)

Max Activating Token Index: 661

Text #3

Max Range: 1.3530. Min Range: -1.3530

Max Act: 1.1882. Min Act: -0.0000

Data Index: 470178 (The Pile)

Max Activating Token Index: 910

Text #4

Max Range: 1.3530. Min Range: -1.3530

Max Act: 1.3000. Min Act: -0.0000

Data Index: 1827836 (The Pile)

Max Activating Token Index: 162

Text #5

Max Range: 1.3530. Min Range: -1.3530

Max Act: 1.0368. Min Act: -0.0000

Data Index: 169376 (The Pile)

Max Activating Token Index: 427

Text #6

Max Range: 1.3530. Min Range: -1.3530

Max Act: 1.0400. Min Act: -0.0000

Data Index: 308017 (The Pile)

Max Activating Token Index: 367

Text #7

Max Range: 1.3530. Min Range: -1.3530

Max Act: 0.9127. Min Act: -0.0000

Data Index: 874507 (The Pile)

Max Activating Token Index: 105

Text #8

Max Range: 1.3530. Min Range: -1.3530

Max Act: 0.9316. Min Act: -0.0000

Data Index: 331815 (The Pile)

Max Activating Token Index: 449

Text #9

Max Range: 1.3530. Min Range: -1.3530

Max Act: 0.8957. Min Act: -0.0000

Data Index: 1794375 (The Pile)

Max Activating Token Index: 724

Text #10

Max Range: 1.3530. Min Range: -1.3530

Max Act: 0.9144. Min Act: -0.0000

Data Index: 986201 (The Pile)

Max Activating Token Index: 439

Text #11

Max Range: 1.3530. Min Range: -1.3530

Max Act: 0.8787. Min Act: -0.0000

Data Index: 466828 (The Pile)

Max Activating Token Index: 110

Text #12

Max Range: 1.3530. Min Range: -1.3530

Max Act: 0.9336. Min Act: -0.0000

Data Index: 1443120 (The Pile)

Max Activating Token Index: 997

Text #13

Max Range: 1.3530. Min Range: -1.3530

Max Act: 0.9708. Min Act: -0.0000

Data Index: 1960603 (The Pile)

Max Activating Token Index: 975

Text #14

Max Range: 1.3530. Min Range: -1.3530

Max Act: 0.9231. Min Act: -0.0000

Data Index: 1879448 (The Pile)

Max Activating Token Index: 828

Text #15

Max Range: 1.3530. Min Range: -1.3530

Max Act: 0.8270. Min Act: -0.0000

Data Index: 110884 (The Pile)

Max Activating Token Index: 309

Text #16

Max Range: 1.3530. Min Range: -1.3530

Max Act: 0.8393. Min Act: -0.0000

Data Index: 1881299 (The Pile)

Max Activating Token Index: 53

Text #17

Max Range: 1.3530. Min Range: -1.3530

Max Act: 0.8035. Min Act: -0.0000

Data Index: 58776 (The Pile)

Max Activating Token Index: 695

Text #18

Max Range: 1.3530. Min Range: -1.3530

Max Act: 0.8085. Min Act: -0.0000

Data Index: 1562021 (The Pile)

Max Activating Token Index: 184

Text #19

Max Range: 1.3530. Min Range: -1.3530

Max Act: 0.8097. Min Act: -0.0000

Data Index: 966211 (The Pile)

Max Activating Token Index: 815