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

Dataset: The Pile

Neuron 1846 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: 0.7406. Min Range: -0.7406

Max Act: 0.7406. Min Act: -0.0000

Data Index: 53206 (The Pile)

Max Activating Token Index: 516

Text #1

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.7296. Min Act: -0.0000

Data Index: 1505696 (The Pile)

Max Activating Token Index: 461

Text #2

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.7396. Min Act: -0.0000

Data Index: 1545041 (The Pile)

Max Activating Token Index: 566

Text #3

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.7219. Min Act: -0.0000

Data Index: 608253 (The Pile)

Max Activating Token Index: 283

Text #4

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.6671. Min Act: -0.0000

Data Index: 1425620 (The Pile)

Max Activating Token Index: 539

Text #5

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.6535. Min Act: -0.0000

Data Index: 1785959 (The Pile)

Max Activating Token Index: 1017

Text #6

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.6770. Min Act: -0.0000

Data Index: 1914870 (The Pile)

Max Activating Token Index: 792

Text #7

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.6682. Min Act: -0.0000

Data Index: 1994852 (The Pile)

Max Activating Token Index: 632

Text #8

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5970. Min Act: -0.0000

Data Index: 1525961 (The Pile)

Max Activating Token Index: 725

Text #9

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.6058. Min Act: -0.0000

Data Index: 1092340 (The Pile)

Max Activating Token Index: 322

Text #10

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.6716. Min Act: -0.0000

Data Index: 618842 (The Pile)

Max Activating Token Index: 807

Text #11

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.6112. Min Act: -0.0000

Data Index: 994071 (The Pile)

Max Activating Token Index: 181

Text #12

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.6467. Min Act: -0.0000

Data Index: 1213783 (The Pile)

Max Activating Token Index: 823

Text #13

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.6060. Min Act: -0.0000

Data Index: 46236 (The Pile)

Max Activating Token Index: 1012

Text #14

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5899. Min Act: -0.0000

Data Index: 1199279 (The Pile)

Max Activating Token Index: 598

Text #15

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.6160. Min Act: -0.0000

Data Index: 819252 (The Pile)

Max Activating Token Index: 849

Text #16

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.6038. Min Act: -0.0000

Data Index: 1816115 (The Pile)

Max Activating Token Index: 438

Text #17

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.6238. Min Act: -0.0000

Data Index: 23119 (The Pile)

Max Activating Token Index: 172

Text #18

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.6180. Min Act: -0.0000

Data Index: 1073744 (The Pile)

Max Activating Token Index: 575

Text #19

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5705. Min Act: -0.0000

Data Index: 233461 (The Pile)

Max Activating Token Index: 711