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

Dataset: The Pile

Neuron 1820 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: 1.8797. Min Range: -1.8797

Max Act: 1.8797. Min Act: -0.0000

Data Index: 797058 (The Pile)

Max Activating Token Index: 189

Text #1

Max Range: 1.8797. Min Range: -1.8797

Max Act: 1.5427. Min Act: -0.0000

Data Index: 1414466 (The Pile)

Max Activating Token Index: 805

Text #2

Max Range: 1.8797. Min Range: -1.8797

Max Act: 1.4922. Min Act: -0.0000

Data Index: 270787 (The Pile)

Max Activating Token Index: 348

Text #3

Max Range: 1.8797. Min Range: -1.8797

Max Act: 1.6376. Min Act: -0.0000

Data Index: 865479 (The Pile)

Max Activating Token Index: 466

Text #4

Max Range: 1.8797. Min Range: -1.8797

Max Act: 1.4653. Min Act: -0.0000

Data Index: 733626 (The Pile)

Max Activating Token Index: 427

Text #5

Max Range: 1.8797. Min Range: -1.8797

Max Act: 1.5161. Min Act: -0.0000

Data Index: 1917861 (The Pile)

Max Activating Token Index: 878

Text #6

Max Range: 1.8797. Min Range: -1.8797

Max Act: 1.5911. Min Act: -0.0000

Data Index: 267670 (The Pile)

Max Activating Token Index: 333

Text #7

Max Range: 1.8797. Min Range: -1.8797

Max Act: 1.4068. Min Act: -0.0000

Data Index: 215050 (The Pile)

Max Activating Token Index: 134

Text #8

Max Range: 1.8797. Min Range: -1.8797

Max Act: 1.5602. Min Act: -0.0000

Data Index: 1411402 (The Pile)

Max Activating Token Index: 363

Text #9

Max Range: 1.8797. Min Range: -1.8797

Max Act: 1.4565. Min Act: -0.0000

Data Index: 643798 (The Pile)

Max Activating Token Index: 559

Text #10

Max Range: 1.8797. Min Range: -1.8797

Max Act: 1.3644. Min Act: -0.0000

Data Index: 1831209 (The Pile)

Max Activating Token Index: 98

Text #11

Max Range: 1.8797. Min Range: -1.8797

Max Act: 1.3653. Min Act: -0.0000

Data Index: 1524480 (The Pile)

Max Activating Token Index: 689

Text #12

Max Range: 1.8797. Min Range: -1.8797

Max Act: 1.4273. Min Act: -0.0000

Data Index: 191428 (The Pile)

Max Activating Token Index: 89

Text #13

Max Range: 1.8797. Min Range: -1.8797

Max Act: 1.4186. Min Act: -0.0000

Data Index: 1120270 (The Pile)

Max Activating Token Index: 196

Text #14

Max Range: 1.8797. Min Range: -1.8797

Max Act: 1.3903. Min Act: -0.0000

Data Index: 965232 (The Pile)

Max Activating Token Index: 295

Text #15

Max Range: 1.8797. Min Range: -1.8797

Max Act: 1.2927. Min Act: -0.0000

Data Index: 1613807 (The Pile)

Max Activating Token Index: 201

Text #16

Max Range: 1.8797. Min Range: -1.8797

Max Act: 1.3335. Min Act: -0.0000

Data Index: 543700 (The Pile)

Max Activating Token Index: 974

Text #17

Max Range: 1.8797. Min Range: -1.8797

Max Act: 1.3214. Min Act: -0.0000

Data Index: 262616 (The Pile)

Max Activating Token Index: 706

Text #18

Max Range: 1.8797. Min Range: -1.8797

Max Act: 1.3160. Min Act: -0.0000

Data Index: 1701465 (The Pile)

Max Activating Token Index: 382

Text #19

Max Range: 1.8797. Min Range: -1.8797

Max Act: 1.3196. Min Act: -0.0000

Data Index: 1808029 (The Pile)

Max Activating Token Index: 181