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

Dataset: The Pile

Neuron 3717 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.9557. Min Act: -0.0000

Data Index: 777303 (The Pile)

Max Activating Token Index: 324

Text #1

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.8704. Min Act: -0.0000

Data Index: 905422 (The Pile)

Max Activating Token Index: 189

Text #2

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.6473. Min Act: -0.0000

Data Index: 1490075 (The Pile)

Max Activating Token Index: 105

Text #3

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.7208. Min Act: -0.0000

Data Index: 1979843 (The Pile)

Max Activating Token Index: 753

Text #4

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.6469. Min Act: -0.0000

Data Index: 940689 (The Pile)

Max Activating Token Index: 1020

Text #5

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.7503. Min Act: -0.0000

Data Index: 1449571 (The Pile)

Max Activating Token Index: 975

Text #6

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.6138. Min Act: -0.0000

Data Index: 1720889 (The Pile)

Max Activating Token Index: 303

Text #7

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.6379. Min Act: -0.0000

Data Index: 692307 (The Pile)

Max Activating Token Index: 448

Text #8

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.6181. Min Act: -0.0000

Data Index: 347963 (The Pile)

Max Activating Token Index: 276

Text #9

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.7197. Min Act: -0.0000

Data Index: 714065 (The Pile)

Max Activating Token Index: 74

Text #10

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.7172. Min Act: -0.0000

Data Index: 1799594 (The Pile)

Max Activating Token Index: 737

Text #11

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.6317. Min Act: -0.0000

Data Index: 1864971 (The Pile)

Max Activating Token Index: 203

Text #12

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.6886. Min Act: -0.0000

Data Index: 1630300 (The Pile)

Max Activating Token Index: 790

Text #13

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.6773. Min Act: -0.0000

Data Index: 683550 (The Pile)

Max Activating Token Index: 863

Text #14

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.4810. Min Act: -0.0000

Data Index: 1678917 (The Pile)

Max Activating Token Index: 653

Text #15

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.5646. Min Act: -0.0000

Data Index: 322895 (The Pile)

Max Activating Token Index: 846

Text #16

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.5279. Min Act: -0.0000

Data Index: 366732 (The Pile)

Max Activating Token Index: 191

Text #17

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.5251. Min Act: -0.0000

Data Index: 1249884 (The Pile)

Max Activating Token Index: 619

Text #18

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.5538. Min Act: -0.0000

Data Index: 776178 (The Pile)

Max Activating Token Index: 970

Text #19

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.5851. Min Act: -0.0000

Data Index: 1736188 (The Pile)

Max Activating Token Index: 461