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

Dataset: The Pile

Neuron 443 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.7732. Min Act: -0.0000

Data Index: 576903 (The Pile)

Max Activating Token Index: 739

Text #1

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.6558. Min Act: -0.0000

Data Index: 723828 (The Pile)

Max Activating Token Index: 459

Text #2

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.6400. Min Act: -0.0000

Data Index: 596923 (The Pile)

Max Activating Token Index: 637

Text #3

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.5999. Min Act: -0.0000

Data Index: 1862052 (The Pile)

Max Activating Token Index: 142

Text #4

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.6227. Min Act: -0.0000

Data Index: 29193 (The Pile)

Max Activating Token Index: 554

Text #5

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.6162. Min Act: -0.0000

Data Index: 778720 (The Pile)

Max Activating Token Index: 816

Text #6

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.6050. Min Act: -0.0000

Data Index: 524740 (The Pile)

Max Activating Token Index: 988

Text #7

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.5743. Min Act: -0.0000

Data Index: 1796571 (The Pile)

Max Activating Token Index: 901

Text #8

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.5719. Min Act: -0.0000

Data Index: 1477288 (The Pile)

Max Activating Token Index: 170

Text #9

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.5364. Min Act: -0.0000

Data Index: 1486798 (The Pile)

Max Activating Token Index: 225

Text #10

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.5203. Min Act: -0.0000

Data Index: 943928 (The Pile)

Max Activating Token Index: 979

Text #11

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.5455. Min Act: -0.0000

Data Index: 32707 (The Pile)

Max Activating Token Index: 967

Text #12

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.5255. Min Act: -0.0000

Data Index: 1555664 (The Pile)

Max Activating Token Index: 70

Text #13

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.5318. Min Act: -0.0000

Data Index: 825044 (The Pile)

Max Activating Token Index: 960

Text #14

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.5471. Min Act: -0.0000

Data Index: 1559680 (The Pile)

Max Activating Token Index: 311

Text #15

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.5434. Min Act: -0.0000

Data Index: 67054 (The Pile)

Max Activating Token Index: 183

Text #16

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.5075. Min Act: -0.0000

Data Index: 721444 (The Pile)

Max Activating Token Index: 790

Text #17

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.5250. Min Act: -0.0000

Data Index: 1130183 (The Pile)

Max Activating Token Index: 500

Text #18

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.5638. Min Act: -0.0000

Data Index: 1251531 (The Pile)

Max Activating Token Index: 985

Text #19

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.5120. Min Act: -0.0000

Data Index: 703094 (The Pile)

Max Activating Token Index: 931