Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2029 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.7984. Min Range: -2.7984

Max Act: 2.7984. Min Act: -0.0000

Data Index: 78786 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 2.7984. Min Range: -2.7984

Max Act: 2.7022. Min Act: -0.0000

Data Index: 679490 (C4 (Web Text))

Max Activating Token Index: 413

Text #2

Max Range: 2.7984. Min Range: -2.7984

Max Act: 2.4667. Min Act: -0.0000

Data Index: 669575 (C4 (Web Text))

Max Activating Token Index: 982

Text #3

Max Range: 2.7984. Min Range: -2.7984

Max Act: 2.5094. Min Act: -0.0000

Data Index: 366400 (C4 (Web Text))

Max Activating Token Index: 892

Text #4

Max Range: 2.7984. Min Range: -2.7984

Max Act: 2.3252. Min Act: -0.0000

Data Index: 465807 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 2.7984. Min Range: -2.7984

Max Act: 2.3118. Min Act: -0.0000

Data Index: 485759 (C4 (Web Text))

Max Activating Token Index: 403

Text #6

Max Range: 2.7984. Min Range: -2.7984

Max Act: 2.2752. Min Act: -0.0000

Data Index: 1033369 (C4 (Web Text))

Max Activating Token Index: 7

Text #7

Max Range: 2.7984. Min Range: -2.7984

Max Act: 2.1561. Min Act: -0.0000

Data Index: 535376 (C4 (Web Text))

Max Activating Token Index: 479

Text #8

Max Range: 2.7984. Min Range: -2.7984

Max Act: 2.1411. Min Act: -0.0000

Data Index: 383234 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 2.7984. Min Range: -2.7984

Max Act: 2.1974. Min Act: -0.0000

Data Index: 217366 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 2.7984. Min Range: -2.7984

Max Act: 2.2758. Min Act: -0.0000

Data Index: 1261401 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 2.7984. Min Range: -2.7984

Max Act: 2.1404. Min Act: -0.0000

Data Index: 1059410 (C4 (Web Text))

Max Activating Token Index: 978

Text #12

Max Range: 2.7984. Min Range: -2.7984

Max Act: 2.2418. Min Act: -0.0000

Data Index: 1314312 (C4 (Web Text))

Max Activating Token Index: 834

Text #13

Max Range: 2.7984. Min Range: -2.7984

Max Act: 2.0159. Min Act: -0.0000

Data Index: 1029023 (C4 (Web Text))

Max Activating Token Index: 944

Text #14

Max Range: 2.7984. Min Range: -2.7984

Max Act: 2.1565. Min Act: -0.0000

Data Index: 1227394 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 2.7984. Min Range: -2.7984

Max Act: 2.1354. Min Act: -0.0000

Data Index: 1095576 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 2.7984. Min Range: -2.7984

Max Act: 2.1531. Min Act: -0.0000

Data Index: 376831 (C4 (Web Text))

Max Activating Token Index: 907

Text #17

Max Range: 2.7984. Min Range: -2.7984

Max Act: 2.0122. Min Act: -0.0000

Data Index: 322077 (C4 (Web Text))

Max Activating Token Index: 868

Text #18

Max Range: 2.7984. Min Range: -2.7984

Max Act: 2.0992. Min Act: -0.0000

Data Index: 817409 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 2.7984. Min Range: -2.7984

Max Act: 2.0858. Min Act: -0.0000

Data Index: 1183758 (C4 (Web Text))

Max Activating Token Index: 5