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

Dataset: The Pile

Neuron 3558 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: 0.6737. Min Range: -0.6737

Max Act: 0.6737. Min Act: -0.0000

Data Index: 1426633 (The Pile)

Max Activating Token Index: 135

Text #1

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.5720. Min Act: -0.0000

Data Index: 1800181 (The Pile)

Max Activating Token Index: 978

Text #2

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.5408. Min Act: -0.0000

Data Index: 194100 (The Pile)

Max Activating Token Index: 842

Text #3

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.5461. Min Act: -0.0000

Data Index: 1874505 (The Pile)

Max Activating Token Index: 832

Text #4

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.5164. Min Act: -0.0000

Data Index: 1913229 (The Pile)

Max Activating Token Index: 230

Text #5

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.5055. Min Act: -0.0000

Data Index: 213550 (The Pile)

Max Activating Token Index: 261

Text #6

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.5019. Min Act: -0.0000

Data Index: 1282768 (The Pile)

Max Activating Token Index: 164

Text #7

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.4821. Min Act: -0.0000

Data Index: 1701070 (The Pile)

Max Activating Token Index: 804

Text #8

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.4932. Min Act: -0.0000

Data Index: 811634 (The Pile)

Max Activating Token Index: 319

Text #9

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.5118. Min Act: -0.0000

Data Index: 716788 (The Pile)

Max Activating Token Index: 970

Text #10

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.5038. Min Act: -0.0000

Data Index: 1348999 (The Pile)

Max Activating Token Index: 351

Text #11

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.4651. Min Act: -0.0000

Data Index: 1199500 (The Pile)

Max Activating Token Index: 568

Text #12

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.4926. Min Act: -0.0000

Data Index: 539712 (The Pile)

Max Activating Token Index: 124

Text #13

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.4639. Min Act: -0.0000

Data Index: 1005160 (The Pile)

Max Activating Token Index: 210

Text #14

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.4767. Min Act: 0.0000

Data Index: 344710 (The Pile)

Max Activating Token Index: 53

Text #15

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.4810. Min Act: -0.0000

Data Index: 1807480 (The Pile)

Max Activating Token Index: 939

Text #16

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.4680. Min Act: 0.0000

Data Index: 907671 (The Pile)

Max Activating Token Index: 337

Text #17

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.4676. Min Act: -0.0000

Data Index: 1217235 (The Pile)

Max Activating Token Index: 741

Text #18

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.4782. Min Act: -0.0000

Data Index: 899584 (The Pile)

Max Activating Token Index: 465

Text #19

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.4319. Min Act: -0.0000

Data Index: 827083 (The Pile)

Max Activating Token Index: 686