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

Dataset: The Pile

Neuron 365 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0948. Min Range: -1.0948

Max Act: 1.0948. Min Act: -0.0000

Data Index: 1705814 (The Pile)

Max Activating Token Index: 1019

Text #1

Max Range: 1.0948. Min Range: -1.0948

Max Act: 1.0146. Min Act: -0.0000

Data Index: 167636 (The Pile)

Max Activating Token Index: 1010

Text #2

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.9951. Min Act: -0.0000

Data Index: 1495277 (The Pile)

Max Activating Token Index: 1020

Text #3

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.9586. Min Act: -0.0000

Data Index: 862494 (The Pile)

Max Activating Token Index: 886

Text #4

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.8571. Min Act: -0.0000

Data Index: 517343 (The Pile)

Max Activating Token Index: 181

Text #5

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.8294. Min Act: -0.0000

Data Index: 120503 (The Pile)

Max Activating Token Index: 257

Text #6

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.9020. Min Act: 0.0000

Data Index: 1282697 (The Pile)

Max Activating Token Index: 1009

Text #7

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.8840. Min Act: -0.0000

Data Index: 787873 (The Pile)

Max Activating Token Index: 84

Text #8

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.8729. Min Act: 0.0000

Data Index: 951476 (The Pile)

Max Activating Token Index: 1018

Text #9

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.9187. Min Act: 0.0000

Data Index: 1026508 (The Pile)

Max Activating Token Index: 999

Text #10

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.8438. Min Act: -0.0000

Data Index: 1934354 (The Pile)

Max Activating Token Index: 378

Text #11

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.8429. Min Act: 0.0000

Data Index: 562776 (The Pile)

Max Activating Token Index: 375

Text #12

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.9016. Min Act: -0.0000

Data Index: 369367 (The Pile)

Max Activating Token Index: 978

Text #13

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.8714. Min Act: -0.0000

Data Index: 845600 (The Pile)

Max Activating Token Index: 1006

Text #14

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.8130. Min Act: -0.0000

Data Index: 1539080 (The Pile)

Max Activating Token Index: 947

Text #15

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.8549. Min Act: -0.0000

Data Index: 273277 (The Pile)

Max Activating Token Index: 966

Text #16

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.8519. Min Act: -0.0000

Data Index: 1863015 (The Pile)

Max Activating Token Index: 226

Text #17

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.7911. Min Act: -0.0000

Data Index: 916071 (The Pile)

Max Activating Token Index: 320

Text #18

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.8021. Min Act: -0.0000

Data Index: 1874966 (The Pile)

Max Activating Token Index: 991

Text #19

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.7756. Min Act: 0.0000

Data Index: 430685 (The Pile)

Max Activating Token Index: 1012