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

Dataset: The Pile

Neuron 579 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.9946. Min Act: -0.0000

Data Index: 1818762 (The Pile)

Max Activating Token Index: 487

Text #1

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.7569. Min Act: -0.0000

Data Index: 1213062 (The Pile)

Max Activating Token Index: 941

Text #2

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.7416. Min Act: -0.0000

Data Index: 1597824 (The Pile)

Max Activating Token Index: 998

Text #3

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.9210. Min Act: -0.0000

Data Index: 1669362 (The Pile)

Max Activating Token Index: 749

Text #4

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.6284. Min Act: -0.0000

Data Index: 630724 (The Pile)

Max Activating Token Index: 912

Text #5

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.6348. Min Act: -0.0000

Data Index: 1569109 (The Pile)

Max Activating Token Index: 964

Text #6

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.5313. Min Act: -0.0000

Data Index: 866958 (The Pile)

Max Activating Token Index: 314

Text #7

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.3642. Min Act: -0.0000

Data Index: 446579 (The Pile)

Max Activating Token Index: 121

Text #8

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.5043. Min Act: -0.0000

Data Index: 9646 (The Pile)

Max Activating Token Index: 472

Text #9

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.4716. Min Act: -0.0000

Data Index: 1782980 (The Pile)

Max Activating Token Index: 500

Text #10

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.2803. Min Act: -0.0000

Data Index: 1420545 (The Pile)

Max Activating Token Index: 251

Text #11

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.3972. Min Act: -0.0000

Data Index: 1130302 (The Pile)

Max Activating Token Index: 455

Text #12

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.3798. Min Act: -0.0000

Data Index: 809515 (The Pile)

Max Activating Token Index: 114

Text #13

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.5468. Min Act: -0.0000

Data Index: 505954 (The Pile)

Max Activating Token Index: 213

Text #14

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.5281. Min Act: -0.0000

Data Index: 474377 (The Pile)

Max Activating Token Index: 864

Text #15

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.2253. Min Act: -0.0000

Data Index: 1442571 (The Pile)

Max Activating Token Index: 723

Text #16

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.3820. Min Act: -0.0000

Data Index: 289845 (The Pile)

Max Activating Token Index: 204

Text #17

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.3455. Min Act: -0.0000

Data Index: 88129 (The Pile)

Max Activating Token Index: 1009

Text #18

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.3255. Min Act: -0.0000

Data Index: 1836766 (The Pile)

Max Activating Token Index: 415

Text #19

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.1643. Min Act: -0.0000

Data Index: 1867460 (The Pile)

Max Activating Token Index: 691