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

Dataset: The Pile

Neuron 617 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9112. Min Range: -0.9112

Max Act: 0.6550. Min Act: -0.0000

Data Index: 1188935 (The Pile)

Max Activating Token Index: 560

Text #1

Max Range: 0.9112. Min Range: -0.9112

Max Act: 0.8232. Min Act: -0.0000

Data Index: 437860 (The Pile)

Max Activating Token Index: 754

Text #2

Max Range: 0.9112. Min Range: -0.9112

Max Act: 0.7948. Min Act: -0.0000

Data Index: 738743 (The Pile)

Max Activating Token Index: 468

Text #3

Max Range: 0.9112. Min Range: -0.9112

Max Act: 0.8196. Min Act: -0.0000

Data Index: 700586 (The Pile)

Max Activating Token Index: 842

Text #4

Max Range: 0.9112. Min Range: -0.9112

Max Act: 0.9112. Min Act: -0.0000

Data Index: 180899 (The Pile)

Max Activating Token Index: 547

Text #5

Max Range: 0.9112. Min Range: -0.9112

Max Act: 0.8533. Min Act: -0.0000

Data Index: 1827948 (The Pile)

Max Activating Token Index: 956

Text #6

Max Range: 0.9112. Min Range: -0.9112

Max Act: 0.8037. Min Act: -0.0000

Data Index: 1221850 (The Pile)

Max Activating Token Index: 295

Text #7

Max Range: 0.9112. Min Range: -0.9112

Max Act: 0.7765. Min Act: -0.0000

Data Index: 525761 (The Pile)

Max Activating Token Index: 929

Text #8

Max Range: 0.9112. Min Range: -0.9112

Max Act: 0.7262. Min Act: -0.0000

Data Index: 1471117 (The Pile)

Max Activating Token Index: 611

Text #9

Max Range: 0.9112. Min Range: -0.9112

Max Act: 0.7529. Min Act: -0.0000

Data Index: 1677 (The Pile)

Max Activating Token Index: 610

Text #10

Max Range: 0.9112. Min Range: -0.9112

Max Act: 0.7521. Min Act: -0.0000

Data Index: 470494 (The Pile)

Max Activating Token Index: 628

Text #11

Max Range: 0.9112. Min Range: -0.9112

Max Act: 0.7695. Min Act: -0.0000

Data Index: 1341326 (The Pile)

Max Activating Token Index: 451

Text #12

Max Range: 0.9112. Min Range: -0.9112

Max Act: 0.7312. Min Act: -0.0000

Data Index: 1025870 (The Pile)

Max Activating Token Index: 785

Text #13

Max Range: 0.9112. Min Range: -0.9112

Max Act: 0.7166. Min Act: -0.0000

Data Index: 709454 (The Pile)

Max Activating Token Index: 819

Text #14

Max Range: 0.9112. Min Range: -0.9112

Max Act: 0.7526. Min Act: -0.0000

Data Index: 827993 (The Pile)

Max Activating Token Index: 399

Text #15

Max Range: 0.9112. Min Range: -0.9112

Max Act: 0.7061. Min Act: -0.0000

Data Index: 1573182 (The Pile)

Max Activating Token Index: 586

Text #16

Max Range: 0.9112. Min Range: -0.9112

Max Act: 0.7196. Min Act: -0.0000

Data Index: 205893 (The Pile)

Max Activating Token Index: 745

Text #17

Max Range: 0.9112. Min Range: -0.9112

Max Act: 0.6943. Min Act: -0.0000

Data Index: 1758133 (The Pile)

Max Activating Token Index: 783

Text #18

Max Range: 0.9112. Min Range: -0.9112

Max Act: 0.7286. Min Act: -0.0000

Data Index: 1919675 (The Pile)

Max Activating Token Index: 109

Text #19

Max Range: 0.9112. Min Range: -0.9112

Max Act: 0.7347. Min Act: -0.0000

Data Index: 44440 (The Pile)

Max Activating Token Index: 728