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

Dataset: The Pile

Neuron 5117 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.0906. Min Range: -1.0906

Max Act: 1.0906. Min Act: -0.0000

Data Index: 1027972 (The Pile)

Max Activating Token Index: 817

Text #1

Max Range: 1.0906. Min Range: -1.0906

Max Act: 1.0490. Min Act: -0.0000

Data Index: 163410 (The Pile)

Max Activating Token Index: 621

Text #2

Max Range: 1.0906. Min Range: -1.0906

Max Act: 1.0226. Min Act: -0.0000

Data Index: 1834469 (The Pile)

Max Activating Token Index: 554

Text #3

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.9324. Min Act: -0.0000

Data Index: 680956 (The Pile)

Max Activating Token Index: 525

Text #4

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.9780. Min Act: -0.0000

Data Index: 1164987 (The Pile)

Max Activating Token Index: 37

Text #5

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.9703. Min Act: -0.0000

Data Index: 1328554 (The Pile)

Max Activating Token Index: 710

Text #6

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.9860. Min Act: -0.0000

Data Index: 297330 (The Pile)

Max Activating Token Index: 905

Text #7

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.9763. Min Act: -0.0000

Data Index: 881603 (The Pile)

Max Activating Token Index: 14

Text #8

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.8392. Min Act: -0.0000

Data Index: 1455165 (The Pile)

Max Activating Token Index: 727

Text #9

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.8811. Min Act: -0.0000

Data Index: 27124 (The Pile)

Max Activating Token Index: 492

Text #10

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.9049. Min Act: -0.0000

Data Index: 319486 (The Pile)

Max Activating Token Index: 82

Text #11

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.9311. Min Act: -0.0000

Data Index: 1393342 (The Pile)

Max Activating Token Index: 106

Text #12

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.8340. Min Act: -0.0000

Data Index: 274087 (The Pile)

Max Activating Token Index: 635

Text #13

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.9104. Min Act: -0.0000

Data Index: 264948 (The Pile)

Max Activating Token Index: 693

Text #14

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.8555. Min Act: -0.0000

Data Index: 710996 (The Pile)

Max Activating Token Index: 276

Text #15

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.8453. Min Act: -0.0000

Data Index: 1046098 (The Pile)

Max Activating Token Index: 771

Text #16

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.9157. Min Act: -0.0000

Data Index: 377493 (The Pile)

Max Activating Token Index: 665

Text #17

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.8235. Min Act: -0.0000

Data Index: 1065969 (The Pile)

Max Activating Token Index: 109

Text #18

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.8280. Min Act: -0.0000

Data Index: 549279 (The Pile)

Max Activating Token Index: 79

Text #19

Max Range: 1.0906. Min Range: -1.0906

Max Act: 0.8355. Min Act: -0.0000

Data Index: 1134546 (The Pile)

Max Activating Token Index: 14