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

Dataset: The Pile

Neuron 393 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: 1.9108. Min Range: -1.9108

Max Act: 1.9108. Min Act: 0.0000

Data Index: 574770 (The Pile)

Max Activating Token Index: 983

Text #1

Max Range: 1.9108. Min Range: -1.9108

Max Act: 1.6173. Min Act: -0.0000

Data Index: 930422 (The Pile)

Max Activating Token Index: 782

Text #2

Max Range: 1.9108. Min Range: -1.9108

Max Act: 1.2775. Min Act: -0.0000

Data Index: 553189 (The Pile)

Max Activating Token Index: 703

Text #3

Max Range: 1.9108. Min Range: -1.9108

Max Act: 1.2125. Min Act: -0.0000

Data Index: 627128 (The Pile)

Max Activating Token Index: 713

Text #4

Max Range: 1.9108. Min Range: -1.9108

Max Act: 1.2029. Min Act: -0.0000

Data Index: 383076 (The Pile)

Max Activating Token Index: 665

Text #5

Max Range: 1.9108. Min Range: -1.9108

Max Act: 1.0442. Min Act: -0.0000

Data Index: 401021 (The Pile)

Max Activating Token Index: 401

Text #6

Max Range: 1.9108. Min Range: -1.9108

Max Act: 0.9823. Min Act: -0.0000

Data Index: 283556 (The Pile)

Max Activating Token Index: 766

Text #7

Max Range: 1.9108. Min Range: -1.9108

Max Act: 1.0297. Min Act: -0.0000

Data Index: 472066 (The Pile)

Max Activating Token Index: 418

Text #8

Max Range: 1.9108. Min Range: -1.9108

Max Act: 0.9378. Min Act: -0.0000

Data Index: 1530950 (The Pile)

Max Activating Token Index: 1008

Text #9

Max Range: 1.9108. Min Range: -1.9108

Max Act: 0.9235. Min Act: -0.0000

Data Index: 1079724 (The Pile)

Max Activating Token Index: 320

Text #10

Max Range: 1.9108. Min Range: -1.9108

Max Act: 0.9042. Min Act: -0.0000

Data Index: 351441 (The Pile)

Max Activating Token Index: 951

Text #11

Max Range: 1.9108. Min Range: -1.9108

Max Act: 0.8380. Min Act: -0.0000

Data Index: 759832 (The Pile)

Max Activating Token Index: 1008

Text #12

Max Range: 1.9108. Min Range: -1.9108

Max Act: 0.8445. Min Act: -0.0000

Data Index: 1428840 (The Pile)

Max Activating Token Index: 280

Text #13

Max Range: 1.9108. Min Range: -1.9108

Max Act: 0.8944. Min Act: -0.0000

Data Index: 1432681 (The Pile)

Max Activating Token Index: 489

Text #14

Max Range: 1.9108. Min Range: -1.9108

Max Act: 0.8841. Min Act: -0.0000

Data Index: 87053 (The Pile)

Max Activating Token Index: 790

Text #15

Max Range: 1.9108. Min Range: -1.9108

Max Act: 0.9095. Min Act: -0.0000

Data Index: 551424 (The Pile)

Max Activating Token Index: 559

Text #16

Max Range: 1.9108. Min Range: -1.9108

Max Act: 0.9072. Min Act: -0.0000

Data Index: 687300 (The Pile)

Max Activating Token Index: 342

Text #17

Max Range: 1.9108. Min Range: -1.9108

Max Act: 0.8441. Min Act: -0.0000

Data Index: 122506 (The Pile)

Max Activating Token Index: 759

Text #18

Max Range: 1.9108. Min Range: -1.9108

Max Act: 0.8374. Min Act: -0.0000

Data Index: 908780 (The Pile)

Max Activating Token Index: 853

Text #19

Max Range: 1.9108. Min Range: -1.9108

Max Act: 0.8212. Min Act: -0.0000

Data Index: 128253 (The Pile)

Max Activating Token Index: 750