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

Dataset: The Pile

Neuron 3142 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: 1.5170. Min Range: -1.5170

Max Act: 1.5170. Min Act: -0.0000

Data Index: 34172 (The Pile)

Max Activating Token Index: 113

Text #1

Max Range: 1.5170. Min Range: -1.5170

Max Act: 1.2784. Min Act: -0.0000

Data Index: 1716694 (The Pile)

Max Activating Token Index: 266

Text #2

Max Range: 1.5170. Min Range: -1.5170

Max Act: 1.2326. Min Act: -0.0000

Data Index: 320884 (The Pile)

Max Activating Token Index: 162

Text #3

Max Range: 1.5170. Min Range: -1.5170

Max Act: 1.1966. Min Act: -0.0000

Data Index: 1928012 (The Pile)

Max Activating Token Index: 241

Text #4

Max Range: 1.5170. Min Range: -1.5170

Max Act: 1.1544. Min Act: -0.0000

Data Index: 399488 (The Pile)

Max Activating Token Index: 357

Text #5

Max Range: 1.5170. Min Range: -1.5170

Max Act: 1.1411. Min Act: -0.0000

Data Index: 1038141 (The Pile)

Max Activating Token Index: 586

Text #6

Max Range: 1.5170. Min Range: -1.5170

Max Act: 1.1181. Min Act: -0.0000

Data Index: 1019282 (The Pile)

Max Activating Token Index: 372

Text #7

Max Range: 1.5170. Min Range: -1.5170

Max Act: 1.1488. Min Act: -0.0000

Data Index: 1273241 (The Pile)

Max Activating Token Index: 409

Text #8

Max Range: 1.5170. Min Range: -1.5170

Max Act: 1.0610. Min Act: -0.0000

Data Index: 272935 (The Pile)

Max Activating Token Index: 982

Text #9

Max Range: 1.5170. Min Range: -1.5170

Max Act: 1.0702. Min Act: -0.0000

Data Index: 807594 (The Pile)

Max Activating Token Index: 603

Text #10

Max Range: 1.5170. Min Range: -1.5170

Max Act: 1.1277. Min Act: -0.0000

Data Index: 1909842 (The Pile)

Max Activating Token Index: 108

Text #11

Max Range: 1.5170. Min Range: -1.5170

Max Act: 1.1809. Min Act: -0.0000

Data Index: 729158 (The Pile)

Max Activating Token Index: 937

Text #12

Max Range: 1.5170. Min Range: -1.5170

Max Act: 1.1250. Min Act: -0.0000

Data Index: 684517 (The Pile)

Max Activating Token Index: 153

Text #13

Max Range: 1.5170. Min Range: -1.5170

Max Act: 1.1041. Min Act: -0.0000

Data Index: 532352 (The Pile)

Max Activating Token Index: 184

Text #14

Max Range: 1.5170. Min Range: -1.5170

Max Act: 1.1047. Min Act: -0.0000

Data Index: 842362 (The Pile)

Max Activating Token Index: 322

Text #15

Max Range: 1.5170. Min Range: -1.5170

Max Act: 1.0705. Min Act: -0.0000

Data Index: 764825 (The Pile)

Max Activating Token Index: 87

Text #16

Max Range: 1.5170. Min Range: -1.5170

Max Act: 1.0668. Min Act: -0.0000

Data Index: 427193 (The Pile)

Max Activating Token Index: 649

Text #17

Max Range: 1.5170. Min Range: -1.5170

Max Act: 0.8087. Min Act: -0.0000

Data Index: 767409 (The Pile)

Max Activating Token Index: 876

Text #18

Max Range: 1.5170. Min Range: -1.5170

Max Act: 1.0639. Min Act: -0.0000

Data Index: 1539286 (The Pile)

Max Activating Token Index: 180

Text #19

Max Range: 1.5170. Min Range: -1.5170

Max Act: 1.0591. Min Act: -0.0000

Data Index: 1961737 (The Pile)

Max Activating Token Index: 539