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

Dataset: The Pile

Neuron 2392 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1978. Min Act: -0.0000

Data Index: 459262 (The Pile)

Max Activating Token Index: 986

Text #1

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1726. Min Act: -0.0000

Data Index: 1296311 (The Pile)

Max Activating Token Index: 155

Text #2

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1884. Min Act: -0.0000

Data Index: 435523 (The Pile)

Max Activating Token Index: 39

Text #3

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1729. Min Act: -0.0000

Data Index: 193355 (The Pile)

Max Activating Token Index: 63

Text #4

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1899. Min Act: -0.0000

Data Index: 318221 (The Pile)

Max Activating Token Index: 25

Text #5

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1780. Min Act: -0.0000

Data Index: 446646 (The Pile)

Max Activating Token Index: 590

Text #6

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1737. Min Act: -0.0000

Data Index: 748085 (The Pile)

Max Activating Token Index: 77

Text #7

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1742. Min Act: -0.0000

Data Index: 1962149 (The Pile)

Max Activating Token Index: 994

Text #8

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1728. Min Act: -0.0000

Data Index: 1070317 (The Pile)

Max Activating Token Index: 565

Text #9

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1669. Min Act: -0.0000

Data Index: 628013 (The Pile)

Max Activating Token Index: 486

Text #10

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1584. Min Act: -0.0000

Data Index: 1955431 (The Pile)

Max Activating Token Index: 1008

Text #11

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1599. Min Act: -0.0000

Data Index: 1368365 (The Pile)

Max Activating Token Index: 79

Text #12

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1866. Min Act: -0.0000

Data Index: 770133 (The Pile)

Max Activating Token Index: 724

Text #13

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1825. Min Act: -0.0000

Data Index: 212239 (The Pile)

Max Activating Token Index: 13

Text #14

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1468. Min Act: -0.0000

Data Index: 822362 (The Pile)

Max Activating Token Index: 62

Text #15

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1585. Min Act: -0.0000

Data Index: 432559 (The Pile)

Max Activating Token Index: 435

Text #16

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1486. Min Act: -0.0000

Data Index: 1698385 (The Pile)

Max Activating Token Index: 811

Text #17

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1590. Min Act: -0.0000

Data Index: 442349 (The Pile)

Max Activating Token Index: 1005

Text #18

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1765. Min Act: -0.0000

Data Index: 1701915 (The Pile)

Max Activating Token Index: 529

Text #19

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1538. Min Act: -0.0000

Data Index: 1430188 (The Pile)

Max Activating Token Index: 512