Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 652 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1433. Min Act: -0.0000

Data Index: 197496 (The Pile)

Max Activating Token Index: 705

Text #1

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1361. Min Act: -0.0000

Data Index: 1815411 (The Pile)

Max Activating Token Index: 83

Text #2

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1219. Min Act: -0.0000

Data Index: 1137161 (The Pile)

Max Activating Token Index: 855

Text #3

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1189. Min Act: -0.0000

Data Index: 460039 (The Pile)

Max Activating Token Index: 865

Text #4

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0992. Min Act: -0.0000

Data Index: 1477972 (The Pile)

Max Activating Token Index: 596

Text #5

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1003. Min Act: -0.0000

Data Index: 1203732 (The Pile)

Max Activating Token Index: 132

Text #6

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0977. Min Act: -0.0000

Data Index: 339800 (The Pile)

Max Activating Token Index: 56

Text #7

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0982. Min Act: -0.0000

Data Index: 1315867 (The Pile)

Max Activating Token Index: 155

Text #8

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0902. Min Act: -0.0000

Data Index: 415633 (The Pile)

Max Activating Token Index: 752

Text #9

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0931. Min Act: -0.0000

Data Index: 1171054 (The Pile)

Max Activating Token Index: 510

Text #10

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0912. Min Act: -0.0000

Data Index: 777598 (The Pile)

Max Activating Token Index: 63

Text #11

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0843. Min Act: -0.0000

Data Index: 604917 (The Pile)

Max Activating Token Index: 753

Text #12

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0811. Min Act: -0.0000

Data Index: 1304396 (The Pile)

Max Activating Token Index: 169

Text #13

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0808. Min Act: -0.0000

Data Index: 212397 (The Pile)

Max Activating Token Index: 679

Text #14

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0808. Min Act: -0.0000

Data Index: 1489714 (The Pile)

Max Activating Token Index: 851

Text #15

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0823. Min Act: -0.0000

Data Index: 1533596 (The Pile)

Max Activating Token Index: 1002

Text #16

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0826. Min Act: -0.0000

Data Index: 842911 (The Pile)

Max Activating Token Index: 48

Text #17

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0847. Min Act: -0.0000

Data Index: 1282257 (The Pile)

Max Activating Token Index: 869

Text #18

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0816. Min Act: -0.0000

Data Index: 119547 (The Pile)

Max Activating Token Index: 413

Text #19

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0810. Min Act: -0.0000

Data Index: 1286555 (The Pile)

Max Activating Token Index: 42