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

Dataset: The Pile

Neuron 2117 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.8963. Min Act: -0.0000

Data Index: 895834 (The Pile)

Max Activating Token Index: 983

Text #1

Max Range: 1.2036. Min Range: -1.2036

Max Act: 1.1074. Min Act: -0.0000

Data Index: 657156 (The Pile)

Max Activating Token Index: 914

Text #2

Max Range: 1.2036. Min Range: -1.2036

Max Act: 1.2036. Min Act: -0.0000

Data Index: 1421858 (The Pile)

Max Activating Token Index: 530

Text #3

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.8821. Min Act: -0.0000

Data Index: 1864736 (The Pile)

Max Activating Token Index: 882

Text #4

Max Range: 1.2036. Min Range: -1.2036

Max Act: 1.0505. Min Act: -0.0000

Data Index: 300779 (The Pile)

Max Activating Token Index: 78

Text #5

Max Range: 1.2036. Min Range: -1.2036

Max Act: 1.1985. Min Act: -0.0000

Data Index: 581037 (The Pile)

Max Activating Token Index: 459

Text #6

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.9805. Min Act: -0.0000

Data Index: 1306388 (The Pile)

Max Activating Token Index: 454

Text #7

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.9563. Min Act: -0.0000

Data Index: 676326 (The Pile)

Max Activating Token Index: 802

Text #8

Max Range: 1.2036. Min Range: -1.2036

Max Act: 1.0698. Min Act: -0.0000

Data Index: 1004607 (The Pile)

Max Activating Token Index: 44

Text #9

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.8937. Min Act: -0.0000

Data Index: 822523 (The Pile)

Max Activating Token Index: 587

Text #10

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.9959. Min Act: -0.0000

Data Index: 151220 (The Pile)

Max Activating Token Index: 406

Text #11

Max Range: 1.2036. Min Range: -1.2036

Max Act: 1.0269. Min Act: -0.0000

Data Index: 1288207 (The Pile)

Max Activating Token Index: 303

Text #12

Max Range: 1.2036. Min Range: -1.2036

Max Act: 1.0860. Min Act: -0.0000

Data Index: 573944 (The Pile)

Max Activating Token Index: 607

Text #13

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.9246. Min Act: -0.0000

Data Index: 1617379 (The Pile)

Max Activating Token Index: 577

Text #14

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.8921. Min Act: -0.0000

Data Index: 1545996 (The Pile)

Max Activating Token Index: 60

Text #15

Max Range: 1.2036. Min Range: -1.2036

Max Act: 1.0314. Min Act: -0.0000

Data Index: 1230936 (The Pile)

Max Activating Token Index: 79

Text #16

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.8894. Min Act: -0.0000

Data Index: 185233 (The Pile)

Max Activating Token Index: 517

Text #17

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.8494. Min Act: -0.0000

Data Index: 372730 (The Pile)

Max Activating Token Index: 687

Text #18

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.9958. Min Act: -0.0000

Data Index: 1035962 (The Pile)

Max Activating Token Index: 900

Text #19

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.9089. Min Act: -0.0000

Data Index: 1665924 (The Pile)

Max Activating Token Index: 269