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

Dataset: The Pile

Neuron 2837 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: 7.8468. Min Range: -7.8468

Max Act: 7.4489. Min Act: -0.0000

Data Index: 790725 (The Pile)

Max Activating Token Index: 1009

Text #1

Max Range: 7.8468. Min Range: -7.8468

Max Act: 7.5688. Min Act: -0.0000

Data Index: 1050829 (The Pile)

Max Activating Token Index: 430

Text #2

Max Range: 7.8468. Min Range: -7.8468

Max Act: 7.7068. Min Act: -0.0000

Data Index: 1705509 (The Pile)

Max Activating Token Index: 996

Text #3

Max Range: 7.8468. Min Range: -7.8468

Max Act: 7.8468. Min Act: -0.0000

Data Index: 405394 (The Pile)

Max Activating Token Index: 751

Text #4

Max Range: 7.8468. Min Range: -7.8468

Max Act: 7.4127. Min Act: -0.0000

Data Index: 488554 (The Pile)

Max Activating Token Index: 890

Text #5

Max Range: 7.8468. Min Range: -7.8468

Max Act: 7.3186. Min Act: -0.0000

Data Index: 328678 (The Pile)

Max Activating Token Index: 955

Text #6

Max Range: 7.8468. Min Range: -7.8468

Max Act: 7.3034. Min Act: -0.0000

Data Index: 1213033 (The Pile)

Max Activating Token Index: 987

Text #7

Max Range: 7.8468. Min Range: -7.8468

Max Act: 7.2623. Min Act: -0.0000

Data Index: 1257954 (The Pile)

Max Activating Token Index: 918

Text #8

Max Range: 7.8468. Min Range: -7.8468

Max Act: 7.2142. Min Act: -0.0000

Data Index: 1980283 (The Pile)

Max Activating Token Index: 856

Text #9

Max Range: 7.8468. Min Range: -7.8468

Max Act: 7.0692. Min Act: -0.0000

Data Index: 1409932 (The Pile)

Max Activating Token Index: 802

Text #10

Max Range: 7.8468. Min Range: -7.8468

Max Act: 7.3895. Min Act: -0.0000

Data Index: 1732594 (The Pile)

Max Activating Token Index: 931

Text #11

Max Range: 7.8468. Min Range: -7.8468

Max Act: 7.0595. Min Act: -0.0000

Data Index: 1425749 (The Pile)

Max Activating Token Index: 919

Text #12

Max Range: 7.8468. Min Range: -7.8468

Max Act: 6.7069. Min Act: -0.0000

Data Index: 1172108 (The Pile)

Max Activating Token Index: 775

Text #13

Max Range: 7.8468. Min Range: -7.8468

Max Act: 7.2423. Min Act: -0.0000

Data Index: 508574 (The Pile)

Max Activating Token Index: 1018

Text #14

Max Range: 7.8468. Min Range: -7.8468

Max Act: 7.0520. Min Act: -0.0000

Data Index: 1805037 (The Pile)

Max Activating Token Index: 983

Text #15

Max Range: 7.8468. Min Range: -7.8468

Max Act: 7.2000. Min Act: -0.0000

Data Index: 1073368 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 7.8468. Min Range: -7.8468

Max Act: 6.6318. Min Act: -0.0000

Data Index: 518847 (The Pile)

Max Activating Token Index: 700

Text #17

Max Range: 7.8468. Min Range: -7.8468

Max Act: 6.9692. Min Act: -0.0000

Data Index: 1919353 (The Pile)

Max Activating Token Index: 707

Text #18

Max Range: 7.8468. Min Range: -7.8468

Max Act: 6.9084. Min Act: -0.0000

Data Index: 339291 (The Pile)

Max Activating Token Index: 893

Text #19

Max Range: 7.8468. Min Range: -7.8468

Max Act: 7.0591. Min Act: -0.0000

Data Index: 1623405 (The Pile)

Max Activating Token Index: 874