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

Dataset: The Pile

Neuron 3590 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: 1.8805. Min Range: -1.8805

Max Act: 1.8805. Min Act: -0.0000

Data Index: 482062 (The Pile)

Max Activating Token Index: 311

Text #1

Max Range: 1.8805. Min Range: -1.8805

Max Act: 1.8176. Min Act: -0.0000

Data Index: 622942 (The Pile)

Max Activating Token Index: 100

Text #2

Max Range: 1.8805. Min Range: -1.8805

Max Act: 1.7264. Min Act: -0.0000

Data Index: 1947848 (The Pile)

Max Activating Token Index: 50

Text #3

Max Range: 1.8805. Min Range: -1.8805

Max Act: 1.8249. Min Act: -0.0000

Data Index: 265807 (The Pile)

Max Activating Token Index: 323

Text #4

Max Range: 1.8805. Min Range: -1.8805

Max Act: 1.6106. Min Act: -0.0000

Data Index: 204742 (The Pile)

Max Activating Token Index: 226

Text #5

Max Range: 1.8805. Min Range: -1.8805

Max Act: 1.6004. Min Act: -0.0000

Data Index: 540835 (The Pile)

Max Activating Token Index: 171

Text #6

Max Range: 1.8805. Min Range: -1.8805

Max Act: 1.4027. Min Act: -0.0000

Data Index: 692431 (The Pile)

Max Activating Token Index: 634

Text #7

Max Range: 1.8805. Min Range: -1.8805

Max Act: 1.5664. Min Act: -0.0000

Data Index: 1865550 (The Pile)

Max Activating Token Index: 580

Text #8

Max Range: 1.8805. Min Range: -1.8805

Max Act: 1.6215. Min Act: -0.0000

Data Index: 910963 (The Pile)

Max Activating Token Index: 187

Text #9

Max Range: 1.8805. Min Range: -1.8805

Max Act: 1.5285. Min Act: -0.0000

Data Index: 276769 (The Pile)

Max Activating Token Index: 528

Text #10

Max Range: 1.8805. Min Range: -1.8805

Max Act: 1.6092. Min Act: -0.0000

Data Index: 366969 (The Pile)

Max Activating Token Index: 620

Text #11

Max Range: 1.8805. Min Range: -1.8805

Max Act: 1.6059. Min Act: -0.0000

Data Index: 1922035 (The Pile)

Max Activating Token Index: 801

Text #12

Max Range: 1.8805. Min Range: -1.8805

Max Act: 1.6771. Min Act: -0.0000

Data Index: 1117466 (The Pile)

Max Activating Token Index: 96

Text #13

Max Range: 1.8805. Min Range: -1.8805

Max Act: 1.6408. Min Act: -0.0000

Data Index: 1496628 (The Pile)

Max Activating Token Index: 752

Text #14

Max Range: 1.8805. Min Range: -1.8805

Max Act: 0.9734. Min Act: -0.0000

Data Index: 1442765 (The Pile)

Max Activating Token Index: 911

Text #15

Max Range: 1.8805. Min Range: -1.8805

Max Act: 1.7101. Min Act: -0.0000

Data Index: 954957 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 1.8805. Min Range: -1.8805

Max Act: 1.4947. Min Act: -0.0000

Data Index: 1460460 (The Pile)

Max Activating Token Index: 374

Text #17

Max Range: 1.8805. Min Range: -1.8805

Max Act: 1.5823. Min Act: -0.0000

Data Index: 1380817 (The Pile)

Max Activating Token Index: 649

Text #18

Max Range: 1.8805. Min Range: -1.8805

Max Act: 1.5414. Min Act: -0.0000

Data Index: 1651425 (The Pile)

Max Activating Token Index: 878

Text #19

Max Range: 1.8805. Min Range: -1.8805

Max Act: 1.6811. Min Act: -0.0000

Data Index: 115839 (The Pile)

Max Activating Token Index: 676