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

Dataset: The Pile

Neuron 1036 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1136. Min Range: -1.1136

Max Act: 0.9380. Min Act: -0.0000

Data Index: 296495 (The Pile)

Max Activating Token Index: 75

Text #1

Max Range: 1.1136. Min Range: -1.1136

Max Act: 0.8933. Min Act: -0.0000

Data Index: 1131834 (The Pile)

Max Activating Token Index: 961

Text #2

Max Range: 1.1136. Min Range: -1.1136

Max Act: 0.9725. Min Act: -0.0000

Data Index: 1485448 (The Pile)

Max Activating Token Index: 544

Text #3

Max Range: 1.1136. Min Range: -1.1136

Max Act: 1.0714. Min Act: -0.0000

Data Index: 1055358 (The Pile)

Max Activating Token Index: 284

Text #4

Max Range: 1.1136. Min Range: -1.1136

Max Act: 0.9675. Min Act: -0.0000

Data Index: 1643618 (The Pile)

Max Activating Token Index: 677

Text #5

Max Range: 1.1136. Min Range: -1.1136

Max Act: 1.0334. Min Act: -0.0000

Data Index: 349051 (The Pile)

Max Activating Token Index: 55

Text #6

Max Range: 1.1136. Min Range: -1.1136

Max Act: 0.9296. Min Act: -0.0000

Data Index: 1547583 (The Pile)

Max Activating Token Index: 75

Text #7

Max Range: 1.1136. Min Range: -1.1136

Max Act: 0.8767. Min Act: -0.0000

Data Index: 1783345 (The Pile)

Max Activating Token Index: 759

Text #8

Max Range: 1.1136. Min Range: -1.1136

Max Act: 1.1136. Min Act: -0.0000

Data Index: 268522 (The Pile)

Max Activating Token Index: 897

Text #9

Max Range: 1.1136. Min Range: -1.1136

Max Act: 0.8771. Min Act: -0.0000

Data Index: 1714310 (The Pile)

Max Activating Token Index: 310

Text #10

Max Range: 1.1136. Min Range: -1.1136

Max Act: 0.7981. Min Act: -0.0000

Data Index: 1702150 (The Pile)

Max Activating Token Index: 610

Text #11

Max Range: 1.1136. Min Range: -1.1136

Max Act: 0.8934. Min Act: -0.0000

Data Index: 1019719 (The Pile)

Max Activating Token Index: 83

Text #12

Max Range: 1.1136. Min Range: -1.1136

Max Act: 0.7700. Min Act: -0.0000

Data Index: 381936 (The Pile)

Max Activating Token Index: 65

Text #13

Max Range: 1.1136. Min Range: -1.1136

Max Act: 0.8129. Min Act: -0.0000

Data Index: 1158958 (The Pile)

Max Activating Token Index: 398

Text #14

Max Range: 1.1136. Min Range: -1.1136

Max Act: 0.8497. Min Act: -0.0000

Data Index: 1835207 (The Pile)

Max Activating Token Index: 633

Text #15

Max Range: 1.1136. Min Range: -1.1136

Max Act: 0.8224. Min Act: -0.0000

Data Index: 353816 (The Pile)

Max Activating Token Index: 827

Text #16

Max Range: 1.1136. Min Range: -1.1136

Max Act: 0.9616. Min Act: -0.0000

Data Index: 867714 (The Pile)

Max Activating Token Index: 229

Text #17

Max Range: 1.1136. Min Range: -1.1136

Max Act: 0.8905. Min Act: -0.0000

Data Index: 1768032 (The Pile)

Max Activating Token Index: 931

Text #18

Max Range: 1.1136. Min Range: -1.1136

Max Act: 0.7471. Min Act: -0.0000

Data Index: 1754082 (The Pile)

Max Activating Token Index: 806

Text #19

Max Range: 1.1136. Min Range: -1.1136

Max Act: 0.7173. Min Act: -0.0000

Data Index: 1322139 (The Pile)

Max Activating Token Index: 253