Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 743 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.8644. Min Act: -0.0000

Data Index: 1576892 (The Pile)

Max Activating Token Index: 988

Text #1

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.8707. Min Act: -0.0000

Data Index: 697142 (The Pile)

Max Activating Token Index: 904

Text #2

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.7675. Min Act: -0.0000

Data Index: 1228653 (The Pile)

Max Activating Token Index: 715

Text #3

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.8127. Min Act: -0.0000

Data Index: 765511 (The Pile)

Max Activating Token Index: 110

Text #4

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.7320. Min Act: -0.0000

Data Index: 610895 (The Pile)

Max Activating Token Index: 256

Text #5

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.7637. Min Act: -0.0000

Data Index: 584511 (The Pile)

Max Activating Token Index: 388

Text #6

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.7042. Min Act: -0.0000

Data Index: 361844 (The Pile)

Max Activating Token Index: 853

Text #7

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.7080. Min Act: -0.0000

Data Index: 1002745 (The Pile)

Max Activating Token Index: 97

Text #8

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.6828. Min Act: -0.0000

Data Index: 723890 (The Pile)

Max Activating Token Index: 174

Text #9

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.6983. Min Act: -0.0000

Data Index: 36009 (The Pile)

Max Activating Token Index: 141

Text #10

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.6488. Min Act: -0.0000

Data Index: 1646468 (The Pile)

Max Activating Token Index: 220

Text #11

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.6958. Min Act: -0.0000

Data Index: 300363 (The Pile)

Max Activating Token Index: 592

Text #12

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.6897. Min Act: -0.0000

Data Index: 1606121 (The Pile)

Max Activating Token Index: 727

Text #13

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.6493. Min Act: -0.0000

Data Index: 1709719 (The Pile)

Max Activating Token Index: 719

Text #14

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.6583. Min Act: -0.0000

Data Index: 544362 (The Pile)

Max Activating Token Index: 198

Text #15

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.6561. Min Act: -0.0000

Data Index: 1801611 (The Pile)

Max Activating Token Index: 819

Text #16

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.6164. Min Act: -0.0000

Data Index: 1604402 (The Pile)

Max Activating Token Index: 28

Text #17

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.6324. Min Act: -0.0000

Data Index: 307854 (The Pile)

Max Activating Token Index: 113

Text #18

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.6200. Min Act: -0.0000

Data Index: 1979058 (The Pile)

Max Activating Token Index: 343

Text #19

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.6438. Min Act: -0.0000

Data Index: 481421 (The Pile)

Max Activating Token Index: 741