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

Dataset: The Pile

Neuron 2737 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6227. Min Range: -0.6227

Max Act: 0.6227. Min Act: -0.0000

Data Index: 1570668 (The Pile)

Max Activating Token Index: 99

Text #1

Max Range: 0.6227. Min Range: -0.6227

Max Act: 0.4767. Min Act: -0.0000

Data Index: 1360332 (The Pile)

Max Activating Token Index: 514

Text #2

Max Range: 0.6227. Min Range: -0.6227

Max Act: 0.6070. Min Act: -0.0000

Data Index: 218963 (The Pile)

Max Activating Token Index: 104

Text #3

Max Range: 0.6227. Min Range: -0.6227

Max Act: 0.5168. Min Act: -0.0000

Data Index: 7745 (The Pile)

Max Activating Token Index: 81

Text #4

Max Range: 0.6227. Min Range: -0.6227

Max Act: 0.5897. Min Act: -0.0000

Data Index: 837549 (The Pile)

Max Activating Token Index: 191

Text #5

Max Range: 0.6227. Min Range: -0.6227

Max Act: 0.4281. Min Act: -0.0000

Data Index: 1775761 (The Pile)

Max Activating Token Index: 79

Text #6

Max Range: 0.6227. Min Range: -0.6227

Max Act: 0.4894. Min Act: -0.0000

Data Index: 1271382 (The Pile)

Max Activating Token Index: 106

Text #7

Max Range: 0.6227. Min Range: -0.6227

Max Act: 0.4877. Min Act: -0.0000

Data Index: 1919715 (The Pile)

Max Activating Token Index: 365

Text #8

Max Range: 0.6227. Min Range: -0.6227

Max Act: 0.4868. Min Act: -0.0000

Data Index: 1845787 (The Pile)

Max Activating Token Index: 70

Text #9

Max Range: 0.6227. Min Range: -0.6227

Max Act: 0.4942. Min Act: -0.0000

Data Index: 68677 (The Pile)

Max Activating Token Index: 484

Text #10

Max Range: 0.6227. Min Range: -0.6227

Max Act: 0.5062. Min Act: -0.0000

Data Index: 254193 (The Pile)

Max Activating Token Index: 279

Text #11

Max Range: 0.6227. Min Range: -0.6227

Max Act: 0.4845. Min Act: -0.0000

Data Index: 663834 (The Pile)

Max Activating Token Index: 119

Text #12

Max Range: 0.6227. Min Range: -0.6227

Max Act: 0.4200. Min Act: -0.0000

Data Index: 970531 (The Pile)

Max Activating Token Index: 36

Text #13

Max Range: 0.6227. Min Range: -0.6227

Max Act: 0.4833. Min Act: -0.0000

Data Index: 424979 (The Pile)

Max Activating Token Index: 747

Text #14

Max Range: 0.6227. Min Range: -0.6227

Max Act: 0.4810. Min Act: -0.0000

Data Index: 898263 (The Pile)

Max Activating Token Index: 81

Text #15

Max Range: 0.6227. Min Range: -0.6227

Max Act: 0.3268. Min Act: -0.0000

Data Index: 1811965 (The Pile)

Max Activating Token Index: 117

Text #16

Max Range: 0.6227. Min Range: -0.6227

Max Act: 0.4480. Min Act: -0.0000

Data Index: 1126357 (The Pile)

Max Activating Token Index: 76

Text #17

Max Range: 0.6227. Min Range: -0.6227

Max Act: 0.4355. Min Act: -0.0000

Data Index: 810321 (The Pile)

Max Activating Token Index: 285

Text #18

Max Range: 0.6227. Min Range: -0.6227

Max Act: 0.4464. Min Act: 0.0000

Data Index: 1911141 (The Pile)

Max Activating Token Index: 484

Text #19

Max Range: 0.6227. Min Range: -0.6227

Max Act: 0.4482. Min Act: -0.0000

Data Index: 302878 (The Pile)

Max Activating Token Index: 429