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

Dataset: The Pile

Neuron 4518 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7122. Min Range: -1.7122

Max Act: 1.7122. Min Act: -0.0000

Data Index: 872832 (The Pile)

Max Activating Token Index: 834

Text #1

Max Range: 1.7122. Min Range: -1.7122

Max Act: 1.3972. Min Act: -0.0000

Data Index: 1330857 (The Pile)

Max Activating Token Index: 103

Text #2

Max Range: 1.7122. Min Range: -1.7122

Max Act: 1.2899. Min Act: -0.0000

Data Index: 1431686 (The Pile)

Max Activating Token Index: 664

Text #3

Max Range: 1.7122. Min Range: -1.7122

Max Act: 1.3120. Min Act: -0.0000

Data Index: 1727506 (The Pile)

Max Activating Token Index: 219

Text #4

Max Range: 1.7122. Min Range: -1.7122

Max Act: 1.2311. Min Act: -0.0000

Data Index: 1650340 (The Pile)

Max Activating Token Index: 244

Text #5

Max Range: 1.7122. Min Range: -1.7122

Max Act: 1.3049. Min Act: -0.0000

Data Index: 1201013 (The Pile)

Max Activating Token Index: 245

Text #6

Max Range: 1.7122. Min Range: -1.7122

Max Act: 1.1285. Min Act: -0.0000

Data Index: 455505 (The Pile)

Max Activating Token Index: 907

Text #7

Max Range: 1.7122. Min Range: -1.7122

Max Act: 1.1844. Min Act: -0.0000

Data Index: 126034 (The Pile)

Max Activating Token Index: 29

Text #8

Max Range: 1.7122. Min Range: -1.7122

Max Act: 1.1465. Min Act: -0.0000

Data Index: 1828183 (The Pile)

Max Activating Token Index: 823

Text #9

Max Range: 1.7122. Min Range: -1.7122

Max Act: 1.1034. Min Act: -0.0000

Data Index: 587534 (The Pile)

Max Activating Token Index: 94

Text #10

Max Range: 1.7122. Min Range: -1.7122

Max Act: 1.2887. Min Act: -0.0000

Data Index: 1665236 (The Pile)

Max Activating Token Index: 153

Text #11

Max Range: 1.7122. Min Range: -1.7122

Max Act: 1.1771. Min Act: -0.0000

Data Index: 1841333 (The Pile)

Max Activating Token Index: 91

Text #12

Max Range: 1.7122. Min Range: -1.7122

Max Act: 1.0281. Min Act: -0.0000

Data Index: 455163 (The Pile)

Max Activating Token Index: 176

Text #13

Max Range: 1.7122. Min Range: -1.7122

Max Act: 1.0269. Min Act: -0.0000

Data Index: 720898 (The Pile)

Max Activating Token Index: 919

Text #14

Max Range: 1.7122. Min Range: -1.7122

Max Act: 1.2225. Min Act: -0.0000

Data Index: 1631656 (The Pile)

Max Activating Token Index: 651

Text #15

Max Range: 1.7122. Min Range: -1.7122

Max Act: 0.9534. Min Act: -0.0000

Data Index: 212694 (The Pile)

Max Activating Token Index: 650

Text #16

Max Range: 1.7122. Min Range: -1.7122

Max Act: 0.9865. Min Act: -0.0000

Data Index: 71062 (The Pile)

Max Activating Token Index: 473

Text #17

Max Range: 1.7122. Min Range: -1.7122

Max Act: 1.0226. Min Act: -0.0000

Data Index: 564700 (The Pile)

Max Activating Token Index: 762

Text #18

Max Range: 1.7122. Min Range: -1.7122

Max Act: 1.0393. Min Act: -0.0000

Data Index: 409929 (The Pile)

Max Activating Token Index: 218

Text #19

Max Range: 1.7122. Min Range: -1.7122

Max Act: 0.9545. Min Act: -0.0000

Data Index: 1910265 (The Pile)

Max Activating Token Index: 948