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

Dataset: The Pile

Neuron 3134 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9036. Min Range: -5.9036

Max Act: 5.9036. Min Act: -0.0000

Data Index: 237258 (The Pile)

Max Activating Token Index: 235

Text #1

Max Range: 5.9036. Min Range: -5.9036

Max Act: 4.2274. Min Act: -0.0000

Data Index: 1172246 (The Pile)

Max Activating Token Index: 599

Text #2

Max Range: 5.9036. Min Range: -5.9036

Max Act: 4.2418. Min Act: -0.0000

Data Index: 1711325 (The Pile)

Max Activating Token Index: 24

Text #3

Max Range: 5.9036. Min Range: -5.9036

Max Act: 4.0242. Min Act: -0.0000

Data Index: 1061839 (The Pile)

Max Activating Token Index: 71

Text #4

Max Range: 5.9036. Min Range: -5.9036

Max Act: 3.9676. Min Act: -0.0000

Data Index: 579699 (The Pile)

Max Activating Token Index: 923

Text #5

Max Range: 5.9036. Min Range: -5.9036

Max Act: 3.8347. Min Act: -0.0000

Data Index: 1305745 (The Pile)

Max Activating Token Index: 199

Text #6

Max Range: 5.9036. Min Range: -5.9036

Max Act: 3.5281. Min Act: -0.0000

Data Index: 1896519 (The Pile)

Max Activating Token Index: 183

Text #7

Max Range: 5.9036. Min Range: -5.9036

Max Act: 3.5114. Min Act: -0.0000

Data Index: 1259808 (The Pile)

Max Activating Token Index: 447

Text #8

Max Range: 5.9036. Min Range: -5.9036

Max Act: 3.1425. Min Act: -0.0000

Data Index: 1117782 (The Pile)

Max Activating Token Index: 960

Text #9

Max Range: 5.9036. Min Range: -5.9036

Max Act: 3.6296. Min Act: -0.0000

Data Index: 1111602 (The Pile)

Max Activating Token Index: 279

Text #10

Max Range: 5.9036. Min Range: -5.9036

Max Act: 3.3984. Min Act: -0.0000

Data Index: 83311 (The Pile)

Max Activating Token Index: 956

Text #11

Max Range: 5.9036. Min Range: -5.9036

Max Act: 3.7149. Min Act: -0.0000

Data Index: 1286004 (The Pile)

Max Activating Token Index: 340

Text #12

Max Range: 5.9036. Min Range: -5.9036

Max Act: 2.9293. Min Act: -0.0000

Data Index: 673390 (The Pile)

Max Activating Token Index: 755

Text #13

Max Range: 5.9036. Min Range: -5.9036

Max Act: 3.3712. Min Act: -0.0000

Data Index: 250770 (The Pile)

Max Activating Token Index: 792

Text #14

Max Range: 5.9036. Min Range: -5.9036

Max Act: 3.2146. Min Act: -0.0000

Data Index: 361208 (The Pile)

Max Activating Token Index: 749

Text #15

Max Range: 5.9036. Min Range: -5.9036

Max Act: 2.8624. Min Act: -0.0000

Data Index: 934521 (The Pile)

Max Activating Token Index: 580

Text #16

Max Range: 5.9036. Min Range: -5.9036

Max Act: 3.1731. Min Act: -0.0000

Data Index: 1035775 (The Pile)

Max Activating Token Index: 247

Text #17

Max Range: 5.9036. Min Range: -5.9036

Max Act: 3.2919. Min Act: -0.0000

Data Index: 61502 (The Pile)

Max Activating Token Index: 869

Text #18

Max Range: 5.9036. Min Range: -5.9036

Max Act: 3.1652. Min Act: -0.0000

Data Index: 1061872 (The Pile)

Max Activating Token Index: 106

Text #19

Max Range: 5.9036. Min Range: -5.9036

Max Act: 2.9683. Min Act: -0.0000

Data Index: 1556156 (The Pile)

Max Activating Token Index: 522