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

Dataset: The Pile

Neuron 1540 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.9138. Min Act: -0.0000

Data Index: 393565 (The Pile)

Max Activating Token Index: 838

Text #1

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.7853. Min Act: -0.0000

Data Index: 490212 (The Pile)

Max Activating Token Index: 390

Text #2

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.4293. Min Act: -0.0000

Data Index: 1385745 (The Pile)

Max Activating Token Index: 479

Text #3

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.5843. Min Act: -0.0000

Data Index: 105011 (The Pile)

Max Activating Token Index: 135

Text #4

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.3495. Min Act: -0.0000

Data Index: 1939850 (The Pile)

Max Activating Token Index: 799

Text #5

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.4759. Min Act: -0.0000

Data Index: 80207 (The Pile)

Max Activating Token Index: 991

Text #6

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.4356. Min Act: -0.0000

Data Index: 699576 (The Pile)

Max Activating Token Index: 115

Text #7

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.3573. Min Act: -0.0000

Data Index: 1995787 (The Pile)

Max Activating Token Index: 177

Text #8

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.2997. Min Act: -0.0000

Data Index: 579106 (The Pile)

Max Activating Token Index: 64

Text #9

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.2651. Min Act: -0.0000

Data Index: 741724 (The Pile)

Max Activating Token Index: 26

Text #10

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.3466. Min Act: -0.0000

Data Index: 1180424 (The Pile)

Max Activating Token Index: 321

Text #11

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.2477. Min Act: -0.0000

Data Index: 1785069 (The Pile)

Max Activating Token Index: 533

Text #12

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.3162. Min Act: -0.0000

Data Index: 1867529 (The Pile)

Max Activating Token Index: 507

Text #13

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.3023. Min Act: -0.0000

Data Index: 224744 (The Pile)

Max Activating Token Index: 88

Text #14

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.2225. Min Act: -0.0000

Data Index: 1185165 (The Pile)

Max Activating Token Index: 349

Text #15

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.2199. Min Act: -0.0000

Data Index: 126122 (The Pile)

Max Activating Token Index: 408

Text #16

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.2208. Min Act: -0.0000

Data Index: 558594 (The Pile)

Max Activating Token Index: 24

Text #17

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.2519. Min Act: -0.0000

Data Index: 601303 (The Pile)

Max Activating Token Index: 474

Text #18

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.2236. Min Act: -0.0000

Data Index: 1849007 (The Pile)

Max Activating Token Index: 1002

Text #19

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.1007. Min Act: -0.0000

Data Index: 466075 (The Pile)

Max Activating Token Index: 647