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

Dataset: The Pile

Neuron 975 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: 1.1593. Min Range: -1.1593

Max Act: 1.1593. Min Act: -0.0000

Data Index: 1836670 (The Pile)

Max Activating Token Index: 975

Text #1

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.9422. Min Act: -0.0000

Data Index: 711784 (The Pile)

Max Activating Token Index: 475

Text #2

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.8715. Min Act: -0.0000

Data Index: 1039245 (The Pile)

Max Activating Token Index: 326

Text #3

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.8303. Min Act: -0.0000

Data Index: 1844797 (The Pile)

Max Activating Token Index: 879

Text #4

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.8181. Min Act: -0.0000

Data Index: 1328721 (The Pile)

Max Activating Token Index: 182

Text #5

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.7697. Min Act: -0.0000

Data Index: 196078 (The Pile)

Max Activating Token Index: 1010

Text #6

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.7769. Min Act: -0.0000

Data Index: 1550214 (The Pile)

Max Activating Token Index: 976

Text #7

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.7541. Min Act: -0.0000

Data Index: 107415 (The Pile)

Max Activating Token Index: 547

Text #8

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.7516. Min Act: -0.0000

Data Index: 979784 (The Pile)

Max Activating Token Index: 187

Text #9

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.7962. Min Act: -0.0000

Data Index: 1056259 (The Pile)

Max Activating Token Index: 132

Text #10

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.7080. Min Act: -0.0000

Data Index: 1305190 (The Pile)

Max Activating Token Index: 75

Text #11

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.7261. Min Act: -0.0000

Data Index: 838882 (The Pile)

Max Activating Token Index: 598

Text #12

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.7128. Min Act: -0.0000

Data Index: 513733 (The Pile)

Max Activating Token Index: 537

Text #13

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.6662. Min Act: -0.0000

Data Index: 631726 (The Pile)

Max Activating Token Index: 826

Text #14

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.6614. Min Act: -0.0000

Data Index: 1622437 (The Pile)

Max Activating Token Index: 283

Text #15

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.6690. Min Act: -0.0000

Data Index: 1862798 (The Pile)

Max Activating Token Index: 521

Text #16

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.6654. Min Act: -0.0000

Data Index: 1326788 (The Pile)

Max Activating Token Index: 294

Text #17

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.7213. Min Act: -0.0000

Data Index: 637258 (The Pile)

Max Activating Token Index: 628

Text #18

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.6650. Min Act: -0.0000

Data Index: 115644 (The Pile)

Max Activating Token Index: 430

Text #19

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.6375. Min Act: -0.0000

Data Index: 1339283 (The Pile)

Max Activating Token Index: 824