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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3990 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1971. Min Range: -1.1971

Max Act: 1.1971. Min Act: -0.0000

Data Index: 1059920 (C4 (Web Text))

Max Activating Token Index: 442

Text #1

Max Range: 1.1971. Min Range: -1.1971

Max Act: 1.1799. Min Act: -0.0000

Data Index: 1241650 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 1.1971. Min Range: -1.1971

Max Act: 1.1372. Min Act: -0.0000

Data Index: 1073438 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 1.1971. Min Range: -1.1971

Max Act: 1.1411. Min Act: -0.0000

Data Index: 886348 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 1.1971. Min Range: -1.1971

Max Act: 1.1101. Min Act: -0.0000

Data Index: 767130 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 1.1971. Min Range: -1.1971

Max Act: 1.1262. Min Act: -0.0000

Data Index: 447322 (C4 (Web Text))

Max Activating Token Index: 232

Text #6

Max Range: 1.1971. Min Range: -1.1971

Max Act: 1.0598. Min Act: -0.0000

Data Index: 179765 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 1.1971. Min Range: -1.1971

Max Act: 1.1002. Min Act: -0.0000

Data Index: 1276332 (C4 (Web Text))

Max Activating Token Index: 179

Text #8

Max Range: 1.1971. Min Range: -1.1971

Max Act: 1.0533. Min Act: -0.0000

Data Index: 163527 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 1.1971. Min Range: -1.1971

Max Act: 1.0738. Min Act: -0.0000

Data Index: 1276230 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 1.1971. Min Range: -1.1971

Max Act: 1.1040. Min Act: -0.0000

Data Index: 1121340 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 1.1971. Min Range: -1.1971

Max Act: 1.0375. Min Act: -0.0000

Data Index: 170410 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 1.1971. Min Range: -1.1971

Max Act: 1.0317. Min Act: -0.0000

Data Index: 129964 (C4 (Web Text))

Max Activating Token Index: 778

Text #13

Max Range: 1.1971. Min Range: -1.1971

Max Act: 1.0861. Min Act: -0.0000

Data Index: 613544 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.9957. Min Act: -0.0000

Data Index: 1000153 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 1.1971. Min Range: -1.1971

Max Act: 1.0215. Min Act: -0.0000

Data Index: 894015 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 1.1971. Min Range: -1.1971

Max Act: 1.0180. Min Act: -0.0000

Data Index: 1311935 (C4 (Web Text))

Max Activating Token Index: 920

Text #17

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.9823. Min Act: -0.0000

Data Index: 1289013 (C4 (Web Text))

Max Activating Token Index: 831

Text #18

Max Range: 1.1971. Min Range: -1.1971

Max Act: 1.0366. Min Act: -0.0000

Data Index: 907135 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.9941. Min Act: -0.0000

Data Index: 632905 (C4 (Web Text))

Max Activating Token Index: 897