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

Dataset: The Pile

Neuron 2681 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.4617. Min Act: -0.0000

Data Index: 1669243 (The Pile)

Max Activating Token Index: 82

Text #1

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.4612. Min Act: -0.0000

Data Index: 1338102 (The Pile)

Max Activating Token Index: 23

Text #2

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.4868. Min Act: -0.0000

Data Index: 1256655 (The Pile)

Max Activating Token Index: 696

Text #3

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.4122. Min Act: -0.0000

Data Index: 1684502 (The Pile)

Max Activating Token Index: 153

Text #4

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.4508. Min Act: -0.0000

Data Index: 257537 (The Pile)

Max Activating Token Index: 145

Text #5

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.4757. Min Act: -0.0000

Data Index: 1349314 (The Pile)

Max Activating Token Index: 98

Text #6

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.4464. Min Act: -0.0000

Data Index: 1295272 (The Pile)

Max Activating Token Index: 31

Text #7

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.4638. Min Act: -0.0000

Data Index: 761156 (The Pile)

Max Activating Token Index: 13

Text #8

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.4322. Min Act: -0.0000

Data Index: 223084 (The Pile)

Max Activating Token Index: 4

Text #9

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.4220. Min Act: -0.0000

Data Index: 1540518 (The Pile)

Max Activating Token Index: 1001

Text #10

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.4041. Min Act: -0.0000

Data Index: 836245 (The Pile)

Max Activating Token Index: 27

Text #11

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.4113. Min Act: -0.0000

Data Index: 1344271 (The Pile)

Max Activating Token Index: 6

Text #12

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.3992. Min Act: -0.0000

Data Index: 606371 (The Pile)

Max Activating Token Index: 720

Text #13

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.4163. Min Act: -0.0000

Data Index: 1328347 (The Pile)

Max Activating Token Index: 287

Text #14

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.4741. Min Act: -0.0000

Data Index: 1519973 (The Pile)

Max Activating Token Index: 729

Text #15

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.4046. Min Act: -0.0000

Data Index: 315672 (The Pile)

Max Activating Token Index: 708

Text #16

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.3965. Min Act: -0.0000

Data Index: 34032 (The Pile)

Max Activating Token Index: 97

Text #17

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.3755. Min Act: -0.0000

Data Index: 1726483 (The Pile)

Max Activating Token Index: 308

Text #18

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.4019. Min Act: -0.0000

Data Index: 1147577 (The Pile)

Max Activating Token Index: 766

Text #19

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.4038. Min Act: -0.0000

Data Index: 1541195 (The Pile)

Max Activating Token Index: 15