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

Dataset: The Pile

Neuron 2835 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: 0.6909. Min Range: -0.6909

Max Act: 0.6909. Min Act: -0.0000

Data Index: 1197051 (The Pile)

Max Activating Token Index: 489

Text #1

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.6241. Min Act: -0.0000

Data Index: 1904567 (The Pile)

Max Activating Token Index: 185

Text #2

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.6335. Min Act: -0.0000

Data Index: 1494264 (The Pile)

Max Activating Token Index: 527

Text #3

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.6608. Min Act: -0.0000

Data Index: 539063 (The Pile)

Max Activating Token Index: 587

Text #4

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.6751. Min Act: -0.0000

Data Index: 1501343 (The Pile)

Max Activating Token Index: 120

Text #5

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.4789. Min Act: -0.0000

Data Index: 1059858 (The Pile)

Max Activating Token Index: 101

Text #6

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.6493. Min Act: -0.0000

Data Index: 296606 (The Pile)

Max Activating Token Index: 906

Text #7

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.5229. Min Act: -0.0000

Data Index: 617510 (The Pile)

Max Activating Token Index: 169

Text #8

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.5323. Min Act: -0.0000

Data Index: 1522932 (The Pile)

Max Activating Token Index: 578

Text #9

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.5685. Min Act: -0.0000

Data Index: 529897 (The Pile)

Max Activating Token Index: 76

Text #10

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.4813. Min Act: -0.0000

Data Index: 1139079 (The Pile)

Max Activating Token Index: 148

Text #11

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.5156. Min Act: -0.0000

Data Index: 1132615 (The Pile)

Max Activating Token Index: 883

Text #12

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.5470. Min Act: -0.0000

Data Index: 139272 (The Pile)

Max Activating Token Index: 747

Text #13

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.5535. Min Act: -0.0000

Data Index: 886029 (The Pile)

Max Activating Token Index: 388

Text #14

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.5060. Min Act: -0.0000

Data Index: 1130854 (The Pile)

Max Activating Token Index: 247

Text #15

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.4585. Min Act: -0.0000

Data Index: 589443 (The Pile)

Max Activating Token Index: 1013

Text #16

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.4879. Min Act: -0.0000

Data Index: 1037569 (The Pile)

Max Activating Token Index: 624

Text #17

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.4744. Min Act: -0.0000

Data Index: 1982740 (The Pile)

Max Activating Token Index: 375

Text #18

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.4268. Min Act: -0.0000

Data Index: 817868 (The Pile)

Max Activating Token Index: 529

Text #19

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.4567. Min Act: -0.0000

Data Index: 861578 (The Pile)

Max Activating Token Index: 102