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

Dataset: The Pile

Neuron 4406 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: 0.5487. Min Range: -0.5487

Max Act: 0.5109. Min Act: -0.0000

Data Index: 904573 (The Pile)

Max Activating Token Index: 322

Text #1

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.5487. Min Act: -0.0000

Data Index: 1764194 (The Pile)

Max Activating Token Index: 641

Text #2

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.4732. Min Act: -0.0000

Data Index: 1213358 (The Pile)

Max Activating Token Index: 323

Text #3

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.5259. Min Act: -0.0000

Data Index: 1680489 (The Pile)

Max Activating Token Index: 360

Text #4

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.4156. Min Act: -0.0000

Data Index: 946397 (The Pile)

Max Activating Token Index: 998

Text #5

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.4049. Min Act: -0.0000

Data Index: 97651 (The Pile)

Max Activating Token Index: 631

Text #6

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.3616. Min Act: -0.0000

Data Index: 1213306 (The Pile)

Max Activating Token Index: 83

Text #7

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.3563. Min Act: -0.0000

Data Index: 1608686 (The Pile)

Max Activating Token Index: 472

Text #8

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.3891. Min Act: -0.0000

Data Index: 786607 (The Pile)

Max Activating Token Index: 841

Text #9

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.3629. Min Act: -0.0000

Data Index: 216619 (The Pile)

Max Activating Token Index: 359

Text #10

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.2978. Min Act: -0.0000

Data Index: 1880550 (The Pile)

Max Activating Token Index: 674

Text #11

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.3673. Min Act: -0.0000

Data Index: 1973987 (The Pile)

Max Activating Token Index: 268

Text #12

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.3697. Min Act: -0.0000

Data Index: 1879717 (The Pile)

Max Activating Token Index: 778

Text #13

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.3228. Min Act: -0.0000

Data Index: 1837297 (The Pile)

Max Activating Token Index: 1002

Text #14

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.3489. Min Act: -0.0000

Data Index: 1781578 (The Pile)

Max Activating Token Index: 330

Text #15

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.3519. Min Act: -0.0000

Data Index: 1111090 (The Pile)

Max Activating Token Index: 429

Text #16

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.3272. Min Act: -0.0000

Data Index: 435406 (The Pile)

Max Activating Token Index: 119

Text #17

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.3119. Min Act: -0.0000

Data Index: 1129661 (The Pile)

Max Activating Token Index: 238

Text #18

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.3683. Min Act: -0.0000

Data Index: 440946 (The Pile)

Max Activating Token Index: 339

Text #19

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.3205. Min Act: -0.0000

Data Index: 835492 (The Pile)

Max Activating Token Index: 469