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

Dataset: The Pile

Neuron 4138 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2903. Min Act: -0.0000

Data Index: 960386 (The Pile)

Max Activating Token Index: 432

Text #1

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2427. Min Act: -0.0000

Data Index: 539475 (The Pile)

Max Activating Token Index: 419

Text #2

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2313. Min Act: -0.0000

Data Index: 1480560 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2450. Min Act: -0.0000

Data Index: 165762 (The Pile)

Max Activating Token Index: 945

Text #4

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2360. Min Act: -0.0000

Data Index: 1919474 (The Pile)

Max Activating Token Index: 802

Text #5

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.1995. Min Act: -0.0000

Data Index: 1540033 (The Pile)

Max Activating Token Index: 984

Text #6

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2442. Min Act: -0.0000

Data Index: 1717476 (The Pile)

Max Activating Token Index: 255

Text #7

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2216. Min Act: -0.0000

Data Index: 684686 (The Pile)

Max Activating Token Index: 980

Text #8

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2369. Min Act: -0.0000

Data Index: 1912693 (The Pile)

Max Activating Token Index: 620

Text #9

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2431. Min Act: -0.0000

Data Index: 247356 (The Pile)

Max Activating Token Index: 131

Text #10

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2325. Min Act: -0.0000

Data Index: 786058 (The Pile)

Max Activating Token Index: 832

Text #11

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2329. Min Act: -0.0000

Data Index: 371429 (The Pile)

Max Activating Token Index: 592

Text #12

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2055. Min Act: -0.0000

Data Index: 1195966 (The Pile)

Max Activating Token Index: 196

Text #13

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2062. Min Act: -0.0000

Data Index: 1266836 (The Pile)

Max Activating Token Index: 1021

Text #14

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2514. Min Act: -0.0000

Data Index: 1443458 (The Pile)

Max Activating Token Index: 357

Text #15

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2323. Min Act: -0.0000

Data Index: 1311642 (The Pile)

Max Activating Token Index: 998

Text #16

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2172. Min Act: -0.0000

Data Index: 184063 (The Pile)

Max Activating Token Index: 452

Text #17

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2172. Min Act: -0.0000

Data Index: 1782649 (The Pile)

Max Activating Token Index: 409

Text #18

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2139. Min Act: -0.0000

Data Index: 1499361 (The Pile)

Max Activating Token Index: 727

Text #19

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2267. Min Act: -0.0000

Data Index: 377666 (The Pile)

Max Activating Token Index: 862