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

Dataset: The Pile

Neuron 887 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: 0.4925. Min Range: -0.4925

Max Act: 0.4903. Min Act: -0.0000

Data Index: 1110412 (The Pile)

Max Activating Token Index: 441

Text #1

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.4925. Min Act: -0.0000

Data Index: 1410922 (The Pile)

Max Activating Token Index: 462

Text #2

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.4893. Min Act: -0.0000

Data Index: 313139 (The Pile)

Max Activating Token Index: 436

Text #3

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.4000. Min Act: -0.0000

Data Index: 158969 (The Pile)

Max Activating Token Index: 783

Text #4

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.3966. Min Act: -0.0000

Data Index: 408738 (The Pile)

Max Activating Token Index: 190

Text #5

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.3684. Min Act: -0.0000

Data Index: 33833 (The Pile)

Max Activating Token Index: 578

Text #6

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.3996. Min Act: -0.0000

Data Index: 203254 (The Pile)

Max Activating Token Index: 244

Text #7

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.3970. Min Act: -0.0000

Data Index: 1543639 (The Pile)

Max Activating Token Index: 525

Text #8

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.3661. Min Act: -0.0000

Data Index: 1680657 (The Pile)

Max Activating Token Index: 326

Text #9

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.4119. Min Act: -0.0000

Data Index: 873555 (The Pile)

Max Activating Token Index: 777

Text #10

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.3919. Min Act: -0.0000

Data Index: 632357 (The Pile)

Max Activating Token Index: 721

Text #11

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.3652. Min Act: -0.0000

Data Index: 1309047 (The Pile)

Max Activating Token Index: 314

Text #12

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.3466. Min Act: -0.0000

Data Index: 824236 (The Pile)

Max Activating Token Index: 923

Text #13

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.3389. Min Act: -0.0000

Data Index: 1389548 (The Pile)

Max Activating Token Index: 574

Text #14

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.3525. Min Act: -0.0000

Data Index: 530816 (The Pile)

Max Activating Token Index: 960

Text #15

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.3355. Min Act: -0.0000

Data Index: 1758213 (The Pile)

Max Activating Token Index: 860

Text #16

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.3600. Min Act: -0.0000

Data Index: 1099667 (The Pile)

Max Activating Token Index: 897

Text #17

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.3114. Min Act: -0.0000

Data Index: 1666433 (The Pile)

Max Activating Token Index: 833

Text #18

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.3566. Min Act: -0.0000

Data Index: 1217767 (The Pile)

Max Activating Token Index: 110

Text #19

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.3361. Min Act: -0.0000

Data Index: 1049879 (The Pile)

Max Activating Token Index: 783