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

Dataset: The Pile

Neuron 538 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: 1.6074. Min Range: -1.6074

Max Act: 1.6074. Min Act: -0.0000

Data Index: 351849 (The Pile)

Max Activating Token Index: 667

Text #1

Max Range: 1.6074. Min Range: -1.6074

Max Act: 1.4696. Min Act: -0.0000

Data Index: 1467195 (The Pile)

Max Activating Token Index: 706

Text #2

Max Range: 1.6074. Min Range: -1.6074

Max Act: 1.4717. Min Act: -0.0000

Data Index: 1137661 (The Pile)

Max Activating Token Index: 168

Text #3

Max Range: 1.6074. Min Range: -1.6074

Max Act: 1.3685. Min Act: -0.0000

Data Index: 275351 (The Pile)

Max Activating Token Index: 648

Text #4

Max Range: 1.6074. Min Range: -1.6074

Max Act: 1.3457. Min Act: -0.0000

Data Index: 619744 (The Pile)

Max Activating Token Index: 862

Text #5

Max Range: 1.6074. Min Range: -1.6074

Max Act: 1.3365. Min Act: -0.0000

Data Index: 942973 (The Pile)

Max Activating Token Index: 263

Text #6

Max Range: 1.6074. Min Range: -1.6074

Max Act: 1.3158. Min Act: -0.0000

Data Index: 1889875 (The Pile)

Max Activating Token Index: 623

Text #7

Max Range: 1.6074. Min Range: -1.6074

Max Act: 1.2972. Min Act: -0.0000

Data Index: 884640 (The Pile)

Max Activating Token Index: 420

Text #8

Max Range: 1.6074. Min Range: -1.6074

Max Act: 1.2189. Min Act: -0.0000

Data Index: 1162830 (The Pile)

Max Activating Token Index: 311

Text #9

Max Range: 1.6074. Min Range: -1.6074

Max Act: 1.1253. Min Act: -0.0000

Data Index: 988397 (The Pile)

Max Activating Token Index: 144

Text #10

Max Range: 1.6074. Min Range: -1.6074

Max Act: 1.1883. Min Act: -0.0000

Data Index: 1976692 (The Pile)

Max Activating Token Index: 29

Text #11

Max Range: 1.6074. Min Range: -1.6074

Max Act: 1.2618. Min Act: -0.0000

Data Index: 1865564 (The Pile)

Max Activating Token Index: 409

Text #12

Max Range: 1.6074. Min Range: -1.6074

Max Act: 1.2627. Min Act: -0.0000

Data Index: 1866017 (The Pile)

Max Activating Token Index: 126

Text #13

Max Range: 1.6074. Min Range: -1.6074

Max Act: 1.2527. Min Act: -0.0000

Data Index: 1764206 (The Pile)

Max Activating Token Index: 267

Text #14

Max Range: 1.6074. Min Range: -1.6074

Max Act: 1.2208. Min Act: -0.0000

Data Index: 1488774 (The Pile)

Max Activating Token Index: 1018

Text #15

Max Range: 1.6074. Min Range: -1.6074

Max Act: 1.2228. Min Act: -0.0000

Data Index: 839306 (The Pile)

Max Activating Token Index: 738

Text #16

Max Range: 1.6074. Min Range: -1.6074

Max Act: 1.2174. Min Act: -0.0000

Data Index: 153532 (The Pile)

Max Activating Token Index: 434

Text #17

Max Range: 1.6074. Min Range: -1.6074

Max Act: 1.1486. Min Act: -0.0000

Data Index: 1800457 (The Pile)

Max Activating Token Index: 136

Text #18

Max Range: 1.6074. Min Range: -1.6074

Max Act: 1.1990. Min Act: -0.0000

Data Index: 1493083 (The Pile)

Max Activating Token Index: 553

Text #19

Max Range: 1.6074. Min Range: -1.6074

Max Act: 1.1968. Min Act: -0.0000

Data Index: 1173474 (The Pile)

Max Activating Token Index: 170