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

Dataset: The Pile

Neuron 376 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: 0.7897. Min Range: -0.7897

Max Act: 0.7724. Min Act: -0.0000

Data Index: 274409 (The Pile)

Max Activating Token Index: 669

Text #1

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.7555. Min Act: -0.0000

Data Index: 1874382 (The Pile)

Max Activating Token Index: 566

Text #2

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.7897. Min Act: -0.0000

Data Index: 562681 (The Pile)

Max Activating Token Index: 878

Text #3

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.7545. Min Act: -0.0000

Data Index: 787019 (The Pile)

Max Activating Token Index: 864

Text #4

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.7174. Min Act: -0.0000

Data Index: 297961 (The Pile)

Max Activating Token Index: 521

Text #5

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.7374. Min Act: -0.0000

Data Index: 1026645 (The Pile)

Max Activating Token Index: 323

Text #6

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.7226. Min Act: -0.0000

Data Index: 398939 (The Pile)

Max Activating Token Index: 736

Text #7

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.7667. Min Act: -0.0000

Data Index: 1376288 (The Pile)

Max Activating Token Index: 95

Text #8

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.7267. Min Act: -0.0000

Data Index: 1502490 (The Pile)

Max Activating Token Index: 841

Text #9

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.6858. Min Act: -0.0000

Data Index: 550157 (The Pile)

Max Activating Token Index: 264

Text #10

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.7198. Min Act: -0.0000

Data Index: 1857272 (The Pile)

Max Activating Token Index: 583

Text #11

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.7066. Min Act: -0.0000

Data Index: 347900 (The Pile)

Max Activating Token Index: 627

Text #12

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.6914. Min Act: -0.0000

Data Index: 1144506 (The Pile)

Max Activating Token Index: 505

Text #13

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.6852. Min Act: -0.0000

Data Index: 526017 (The Pile)

Max Activating Token Index: 843

Text #14

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.6872. Min Act: -0.0000

Data Index: 989099 (The Pile)

Max Activating Token Index: 636

Text #15

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.6963. Min Act: -0.0000

Data Index: 1751479 (The Pile)

Max Activating Token Index: 854

Text #16

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.7070. Min Act: -0.0000

Data Index: 1224745 (The Pile)

Max Activating Token Index: 92

Text #17

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.7010. Min Act: -0.0000

Data Index: 1757089 (The Pile)

Max Activating Token Index: 182

Text #18

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.6812. Min Act: -0.0000

Data Index: 621322 (The Pile)

Max Activating Token Index: 614

Text #19

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.6744. Min Act: -0.0000

Data Index: 1971656 (The Pile)

Max Activating Token Index: 101