Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2437 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.9156. Min Act: 0.0000

Data Index: 1798351 (The Pile)

Max Activating Token Index: 152

Text #1

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.8474. Min Act: -0.0000

Data Index: 1998120 (The Pile)

Max Activating Token Index: 303

Text #2

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.6812. Min Act: -0.0000

Data Index: 733915 (The Pile)

Max Activating Token Index: 370

Text #3

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.7155. Min Act: -0.0000

Data Index: 1375561 (The Pile)

Max Activating Token Index: 397

Text #4

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.6277. Min Act: -0.0000

Data Index: 141883 (The Pile)

Max Activating Token Index: 953

Text #5

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.7007. Min Act: -0.0000

Data Index: 1034591 (The Pile)

Max Activating Token Index: 288

Text #6

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.7125. Min Act: -0.0000

Data Index: 931925 (The Pile)

Max Activating Token Index: 568

Text #7

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.6884. Min Act: -0.0000

Data Index: 1178750 (The Pile)

Max Activating Token Index: 934

Text #8

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.7087. Min Act: -0.0000

Data Index: 430884 (The Pile)

Max Activating Token Index: 436

Text #9

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.6542. Min Act: -0.0000

Data Index: 842662 (The Pile)

Max Activating Token Index: 768

Text #10

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.6112. Min Act: -0.0000

Data Index: 1381766 (The Pile)

Max Activating Token Index: 264

Text #11

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.5919. Min Act: -0.0000

Data Index: 1704291 (The Pile)

Max Activating Token Index: 1009

Text #12

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.6247. Min Act: -0.0000

Data Index: 1228371 (The Pile)

Max Activating Token Index: 256

Text #13

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.5914. Min Act: -0.0000

Data Index: 1085445 (The Pile)

Max Activating Token Index: 104

Text #14

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.5665. Min Act: -0.0000

Data Index: 1386973 (The Pile)

Max Activating Token Index: 858

Text #15

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.6173. Min Act: -0.0000

Data Index: 1311435 (The Pile)

Max Activating Token Index: 510

Text #16

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.5942. Min Act: -0.0000

Data Index: 1366618 (The Pile)

Max Activating Token Index: 74

Text #17

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.5889. Min Act: -0.0000

Data Index: 957976 (The Pile)

Max Activating Token Index: 725

Text #18

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.5863. Min Act: -0.0000

Data Index: 1320287 (The Pile)

Max Activating Token Index: 792

Text #19

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.6047. Min Act: -0.0000

Data Index: 1590352 (The Pile)

Max Activating Token Index: 395