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

Dataset: The Pile

Neuron 292 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: 0.6207. Min Range: -0.6207

Max Act: 0.6101. Min Act: -0.0000

Data Index: 999533 (The Pile)

Max Activating Token Index: 209

Text #1

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.6189. Min Act: -0.0000

Data Index: 228016 (The Pile)

Max Activating Token Index: 230

Text #2

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.6207. Min Act: -0.0000

Data Index: 1773586 (The Pile)

Max Activating Token Index: 777

Text #3

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.5110. Min Act: -0.0000

Data Index: 286378 (The Pile)

Max Activating Token Index: 759

Text #4

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.5988. Min Act: -0.0000

Data Index: 863343 (The Pile)

Max Activating Token Index: 284

Text #5

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.5493. Min Act: -0.0000

Data Index: 281890 (The Pile)

Max Activating Token Index: 595

Text #6

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.5638. Min Act: -0.0000

Data Index: 45654 (The Pile)

Max Activating Token Index: 19

Text #7

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.5365. Min Act: -0.0000

Data Index: 1631214 (The Pile)

Max Activating Token Index: 824

Text #8

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.5716. Min Act: -0.0000

Data Index: 558231 (The Pile)

Max Activating Token Index: 793

Text #9

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.5903. Min Act: -0.0000

Data Index: 1840392 (The Pile)

Max Activating Token Index: 593

Text #10

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.5269. Min Act: -0.0000

Data Index: 647920 (The Pile)

Max Activating Token Index: 201

Text #11

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.5478. Min Act: -0.0000

Data Index: 935895 (The Pile)

Max Activating Token Index: 938

Text #12

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.5171. Min Act: -0.0000

Data Index: 1017925 (The Pile)

Max Activating Token Index: 564

Text #13

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.5153. Min Act: -0.0000

Data Index: 1910247 (The Pile)

Max Activating Token Index: 761

Text #14

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.4957. Min Act: -0.0000

Data Index: 615402 (The Pile)

Max Activating Token Index: 370

Text #15

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.4602. Min Act: -0.0000

Data Index: 617058 (The Pile)

Max Activating Token Index: 688

Text #16

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.4573. Min Act: -0.0000

Data Index: 1176276 (The Pile)

Max Activating Token Index: 930

Text #17

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.4454. Min Act: -0.0000

Data Index: 554519 (The Pile)

Max Activating Token Index: 972

Text #18

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.4545. Min Act: -0.0000

Data Index: 1443513 (The Pile)

Max Activating Token Index: 978

Text #19

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.4247. Min Act: -0.0000

Data Index: 202414 (The Pile)

Max Activating Token Index: 489