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

Dataset: The Pile

Neuron 4173 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.5070. Min Act: -0.0000

Data Index: 929008 (The Pile)

Max Activating Token Index: 248

Text #1

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4879. Min Act: -0.0000

Data Index: 314491 (The Pile)

Max Activating Token Index: 847

Text #2

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4643. Min Act: -0.0000

Data Index: 1063449 (The Pile)

Max Activating Token Index: 842

Text #3

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4817. Min Act: -0.0000

Data Index: 653430 (The Pile)

Max Activating Token Index: 82

Text #4

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4509. Min Act: -0.0000

Data Index: 1671044 (The Pile)

Max Activating Token Index: 417

Text #5

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4917. Min Act: -0.0000

Data Index: 737817 (The Pile)

Max Activating Token Index: 382

Text #6

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4388. Min Act: -0.0000

Data Index: 53142 (The Pile)

Max Activating Token Index: 496

Text #7

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4415. Min Act: -0.0000

Data Index: 1368667 (The Pile)

Max Activating Token Index: 802

Text #8

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4494. Min Act: -0.0000

Data Index: 1049392 (The Pile)

Max Activating Token Index: 961

Text #9

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4180. Min Act: -0.0000

Data Index: 224023 (The Pile)

Max Activating Token Index: 168

Text #10

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4133. Min Act: -0.0000

Data Index: 1510820 (The Pile)

Max Activating Token Index: 445

Text #11

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4345. Min Act: -0.0000

Data Index: 1351373 (The Pile)

Max Activating Token Index: 941

Text #12

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4416. Min Act: -0.0000

Data Index: 1975258 (The Pile)

Max Activating Token Index: 674

Text #13

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4394. Min Act: -0.0000

Data Index: 300774 (The Pile)

Max Activating Token Index: 821

Text #14

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4110. Min Act: -0.0000

Data Index: 484356 (The Pile)

Max Activating Token Index: 867

Text #15

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.3967. Min Act: -0.0000

Data Index: 1945227 (The Pile)

Max Activating Token Index: 797

Text #16

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.3931. Min Act: -0.0000

Data Index: 443800 (The Pile)

Max Activating Token Index: 898

Text #17

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4023. Min Act: -0.0000

Data Index: 820470 (The Pile)

Max Activating Token Index: 566

Text #18

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4027. Min Act: -0.0000

Data Index: 63243 (The Pile)

Max Activating Token Index: 484

Text #19

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4049. Min Act: -0.0000

Data Index: 697397 (The Pile)

Max Activating Token Index: 806