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

Dataset: The Pile

Neuron 401 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: 0.8181. Min Range: -0.8181

Max Act: 0.8181. Min Act: -0.0000

Data Index: 797699 (The Pile)

Max Activating Token Index: 59

Text #1

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.7023. Min Act: -0.0000

Data Index: 1505891 (The Pile)

Max Activating Token Index: 466

Text #2

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.6895. Min Act: -0.0000

Data Index: 1551636 (The Pile)

Max Activating Token Index: 927

Text #3

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.7318. Min Act: -0.0000

Data Index: 991227 (The Pile)

Max Activating Token Index: 575

Text #4

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.6755. Min Act: -0.0000

Data Index: 64341 (The Pile)

Max Activating Token Index: 798

Text #5

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.6826. Min Act: -0.0000

Data Index: 772985 (The Pile)

Max Activating Token Index: 336

Text #6

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.6597. Min Act: -0.0000

Data Index: 460306 (The Pile)

Max Activating Token Index: 288

Text #7

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.6589. Min Act: -0.0000

Data Index: 1364028 (The Pile)

Max Activating Token Index: 1009

Text #8

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.5887. Min Act: -0.0000

Data Index: 1946923 (The Pile)

Max Activating Token Index: 838

Text #9

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.6459. Min Act: -0.0000

Data Index: 866454 (The Pile)

Max Activating Token Index: 684

Text #10

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.6907. Min Act: -0.0000

Data Index: 1071998 (The Pile)

Max Activating Token Index: 627

Text #11

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.6446. Min Act: -0.0000

Data Index: 1727050 (The Pile)

Max Activating Token Index: 986

Text #12

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.6347. Min Act: -0.0000

Data Index: 279963 (The Pile)

Max Activating Token Index: 582

Text #13

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.5965. Min Act: -0.0000

Data Index: 577612 (The Pile)

Max Activating Token Index: 934

Text #14

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.5996. Min Act: -0.0000

Data Index: 1001000 (The Pile)

Max Activating Token Index: 893

Text #15

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.5778. Min Act: -0.0000

Data Index: 580055 (The Pile)

Max Activating Token Index: 811

Text #16

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.5779. Min Act: -0.0000

Data Index: 1810680 (The Pile)

Max Activating Token Index: 812

Text #17

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.6439. Min Act: -0.0000

Data Index: 971155 (The Pile)

Max Activating Token Index: 825

Text #18

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.5793. Min Act: -0.0000

Data Index: 1124550 (The Pile)

Max Activating Token Index: 75

Text #19

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.5636. Min Act: -0.0000

Data Index: 1170579 (The Pile)

Max Activating Token Index: 254