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

Dataset: The Pile

Neuron 917 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: 0.8638. Min Range: -0.8638

Max Act: 0.8638. Min Act: -0.0000

Data Index: 1026162 (The Pile)

Max Activating Token Index: 854

Text #1

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.8198. Min Act: -0.0000

Data Index: 1054904 (The Pile)

Max Activating Token Index: 795

Text #2

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.6807. Min Act: -0.0000

Data Index: 1175431 (The Pile)

Max Activating Token Index: 290

Text #3

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.7061. Min Act: -0.0000

Data Index: 902458 (The Pile)

Max Activating Token Index: 635

Text #4

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.6859. Min Act: -0.0000

Data Index: 3479 (The Pile)

Max Activating Token Index: 118

Text #5

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.6864. Min Act: -0.0000

Data Index: 981856 (The Pile)

Max Activating Token Index: 187

Text #6

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.6731. Min Act: -0.0000

Data Index: 360763 (The Pile)

Max Activating Token Index: 162

Text #7

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.7350. Min Act: -0.0000

Data Index: 834901 (The Pile)

Max Activating Token Index: 660

Text #8

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.6576. Min Act: -0.0000

Data Index: 130302 (The Pile)

Max Activating Token Index: 403

Text #9

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.6122. Min Act: -0.0000

Data Index: 1183291 (The Pile)

Max Activating Token Index: 76

Text #10

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.6489. Min Act: -0.0000

Data Index: 1661125 (The Pile)

Max Activating Token Index: 97

Text #11

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.6892. Min Act: -0.0000

Data Index: 1699917 (The Pile)

Max Activating Token Index: 73

Text #12

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.6677. Min Act: -0.0000

Data Index: 529408 (The Pile)

Max Activating Token Index: 201

Text #13

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.6382. Min Act: -0.0000

Data Index: 307915 (The Pile)

Max Activating Token Index: 55

Text #14

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.6305. Min Act: -0.0000

Data Index: 1760683 (The Pile)

Max Activating Token Index: 474

Text #15

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.6204. Min Act: -0.0000

Data Index: 361002 (The Pile)

Max Activating Token Index: 560

Text #16

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.6418. Min Act: -0.0000

Data Index: 1072587 (The Pile)

Max Activating Token Index: 231

Text #17

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.6379. Min Act: -0.0000

Data Index: 644790 (The Pile)

Max Activating Token Index: 135

Text #18

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.6675. Min Act: -0.0000

Data Index: 1715084 (The Pile)

Max Activating Token Index: 822

Text #19

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.6368. Min Act: -0.0000

Data Index: 363695 (The Pile)

Max Activating Token Index: 324