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

Dataset: The Pile

Neuron 5056 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: 1.1040. Min Range: -1.1040

Max Act: 1.1040. Min Act: -0.0000

Data Index: 954396 (The Pile)

Max Activating Token Index: 843

Text #1

Max Range: 1.1040. Min Range: -1.1040

Max Act: 1.0198. Min Act: -0.0000

Data Index: 385194 (The Pile)

Max Activating Token Index: 668

Text #2

Max Range: 1.1040. Min Range: -1.1040

Max Act: 1.0972. Min Act: -0.0000

Data Index: 1208768 (The Pile)

Max Activating Token Index: 849

Text #3

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.9678. Min Act: -0.0000

Data Index: 1062485 (The Pile)

Max Activating Token Index: 574

Text #4

Max Range: 1.1040. Min Range: -1.1040

Max Act: 1.0103. Min Act: -0.0000

Data Index: 4388 (The Pile)

Max Activating Token Index: 68

Text #5

Max Range: 1.1040. Min Range: -1.1040

Max Act: 1.0047. Min Act: -0.0000

Data Index: 1762083 (The Pile)

Max Activating Token Index: 97

Text #6

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.9895. Min Act: -0.0000

Data Index: 47105 (The Pile)

Max Activating Token Index: 585

Text #7

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.9394. Min Act: -0.0000

Data Index: 1322352 (The Pile)

Max Activating Token Index: 938

Text #8

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.8787. Min Act: -0.0000

Data Index: 867051 (The Pile)

Max Activating Token Index: 199

Text #9

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.9387. Min Act: -0.0000

Data Index: 878450 (The Pile)

Max Activating Token Index: 752

Text #10

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.9817. Min Act: -0.0000

Data Index: 706593 (The Pile)

Max Activating Token Index: 439

Text #11

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.9681. Min Act: -0.0000

Data Index: 337977 (The Pile)

Max Activating Token Index: 694

Text #12

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.8404. Min Act: -0.0000

Data Index: 1306990 (The Pile)

Max Activating Token Index: 741

Text #13

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.8995. Min Act: -0.0000

Data Index: 1877859 (The Pile)

Max Activating Token Index: 409

Text #14

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.8139. Min Act: -0.0000

Data Index: 1756830 (The Pile)

Max Activating Token Index: 264

Text #15

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.8815. Min Act: -0.0000

Data Index: 854978 (The Pile)

Max Activating Token Index: 901

Text #16

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.8763. Min Act: -0.0000

Data Index: 1750914 (The Pile)

Max Activating Token Index: 19

Text #17

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.8623. Min Act: -0.0000

Data Index: 933308 (The Pile)

Max Activating Token Index: 525

Text #18

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.8202. Min Act: -0.0000

Data Index: 1619700 (The Pile)

Max Activating Token Index: 135

Text #19

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.8127. Min Act: -0.0000

Data Index: 795218 (The Pile)

Max Activating Token Index: 383