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

Dataset: The Pile

Neuron 1304 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: 5.0465. Min Range: -5.0465

Max Act: 5.0465. Min Act: -0.0000

Data Index: 876959 (The Pile)

Max Activating Token Index: 527

Text #1

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.3537. Min Act: -0.0000

Data Index: 1326613 (The Pile)

Max Activating Token Index: 723

Text #2

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.3208. Min Act: -0.0000

Data Index: 506519 (The Pile)

Max Activating Token Index: 81

Text #3

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.4308. Min Act: -0.0000

Data Index: 537972 (The Pile)

Max Activating Token Index: 270

Text #4

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.9833. Min Act: -0.0000

Data Index: 1698849 (The Pile)

Max Activating Token Index: 1005

Text #5

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.3032. Min Act: -0.0000

Data Index: 1059761 (The Pile)

Max Activating Token Index: 9

Text #6

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.2978. Min Act: -0.0000

Data Index: 193366 (The Pile)

Max Activating Token Index: 721

Text #7

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.0893. Min Act: -0.0000

Data Index: 209293 (The Pile)

Max Activating Token Index: 320

Text #8

Max Range: 5.0465. Min Range: -5.0465

Max Act: 3.9460. Min Act: -0.0000

Data Index: 1053618 (The Pile)

Max Activating Token Index: 677

Text #9

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.1228. Min Act: -0.0000

Data Index: 1848336 (The Pile)

Max Activating Token Index: 408

Text #10

Max Range: 5.0465. Min Range: -5.0465

Max Act: 3.7400. Min Act: -0.0000

Data Index: 751784 (The Pile)

Max Activating Token Index: 839

Text #11

Max Range: 5.0465. Min Range: -5.0465

Max Act: 3.5394. Min Act: -0.0000

Data Index: 174694 (The Pile)

Max Activating Token Index: 397

Text #12

Max Range: 5.0465. Min Range: -5.0465

Max Act: 3.6155. Min Act: -0.0000

Data Index: 1705163 (The Pile)

Max Activating Token Index: 832

Text #13

Max Range: 5.0465. Min Range: -5.0465

Max Act: 3.5385. Min Act: -0.0000

Data Index: 1777341 (The Pile)

Max Activating Token Index: 839

Text #14

Max Range: 5.0465. Min Range: -5.0465

Max Act: 3.8007. Min Act: -0.0000

Data Index: 1200087 (The Pile)

Max Activating Token Index: 759

Text #15

Max Range: 5.0465. Min Range: -5.0465

Max Act: 3.6017. Min Act: -0.0000

Data Index: 488886 (The Pile)

Max Activating Token Index: 971

Text #16

Max Range: 5.0465. Min Range: -5.0465

Max Act: 3.4032. Min Act: -0.0000

Data Index: 1226154 (The Pile)

Max Activating Token Index: 68

Text #17

Max Range: 5.0465. Min Range: -5.0465

Max Act: 3.3745. Min Act: -0.0000

Data Index: 299499 (The Pile)

Max Activating Token Index: 787

Text #18

Max Range: 5.0465. Min Range: -5.0465

Max Act: 3.2986. Min Act: -0.0000

Data Index: 76095 (The Pile)

Max Activating Token Index: 547

Text #19

Max Range: 5.0465. Min Range: -5.0465

Max Act: 3.5453. Min Act: -0.0000

Data Index: 1222857 (The Pile)

Max Activating Token Index: 709