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

Dataset: The Pile

Neuron 2922 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.8585. Min Act: -0.0000

Data Index: 1856391 (The Pile)

Max Activating Token Index: 429

Text #1

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.7923. Min Act: -0.0000

Data Index: 1487423 (The Pile)

Max Activating Token Index: 644

Text #2

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.7271. Min Act: -0.0000

Data Index: 1383708 (The Pile)

Max Activating Token Index: 378

Text #3

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.7216. Min Act: -0.0000

Data Index: 1225261 (The Pile)

Max Activating Token Index: 74

Text #4

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.6931. Min Act: -0.0000

Data Index: 17004 (The Pile)

Max Activating Token Index: 75

Text #5

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.6310. Min Act: -0.0000

Data Index: 1848589 (The Pile)

Max Activating Token Index: 806

Text #6

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.7007. Min Act: -0.0000

Data Index: 313867 (The Pile)

Max Activating Token Index: 101

Text #7

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.6585. Min Act: -0.0000

Data Index: 485683 (The Pile)

Max Activating Token Index: 440

Text #8

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.6337. Min Act: -0.0000

Data Index: 1934200 (The Pile)

Max Activating Token Index: 638

Text #9

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.6495. Min Act: -0.0000

Data Index: 1956841 (The Pile)

Max Activating Token Index: 629

Text #10

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.6434. Min Act: -0.0000

Data Index: 1799841 (The Pile)

Max Activating Token Index: 611

Text #11

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.6629. Min Act: -0.0000

Data Index: 217338 (The Pile)

Max Activating Token Index: 386

Text #12

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.6444. Min Act: -0.0000

Data Index: 1973244 (The Pile)

Max Activating Token Index: 457

Text #13

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.6104. Min Act: -0.0000

Data Index: 565820 (The Pile)

Max Activating Token Index: 47

Text #14

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.6440. Min Act: -0.0000

Data Index: 542008 (The Pile)

Max Activating Token Index: 595

Text #15

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.6232. Min Act: -0.0000

Data Index: 804540 (The Pile)

Max Activating Token Index: 668

Text #16

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.5732. Min Act: -0.0000

Data Index: 1146320 (The Pile)

Max Activating Token Index: 695

Text #17

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.5981. Min Act: -0.0000

Data Index: 987702 (The Pile)

Max Activating Token Index: 577

Text #18

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.5863. Min Act: -0.0000

Data Index: 905938 (The Pile)

Max Activating Token Index: 637

Text #19

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.6219. Min Act: -0.0000

Data Index: 885485 (The Pile)

Max Activating Token Index: 220