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

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

Neuron 1025 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2978. Min Range: -1.2978

Max Act: 1.2978. Min Act: -0.0002

Data Index: 279724 (C4 (Web Text))

Max Activating Token Index: 492

Text #1

Max Range: 1.2978. Min Range: -1.2978

Max Act: 1.1704. Min Act: -0.0001

Data Index: 868823 (C4 (Web Text))

Max Activating Token Index: 418

Text #2

Max Range: 1.2978. Min Range: -1.2978

Max Act: 1.1833. Min Act: -0.0001

Data Index: 859204 (C4 (Web Text))

Max Activating Token Index: 172

Text #3

Max Range: 1.2978. Min Range: -1.2978

Max Act: 1.1810. Min Act: -0.0001

Data Index: 796238 (C4 (Web Text))

Max Activating Token Index: 897

Text #4

Max Range: 1.2978. Min Range: -1.2978

Max Act: 1.1764. Min Act: -0.0002

Data Index: 160710 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 1.2978. Min Range: -1.2978

Max Act: 1.1456. Min Act: -0.0001

Data Index: 469504 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 1.2978. Min Range: -1.2978

Max Act: 1.1984. Min Act: -0.0002

Data Index: 146903 (C4 (Web Text))

Max Activating Token Index: 621

Text #7

Max Range: 1.2978. Min Range: -1.2978

Max Act: 1.0729. Min Act: -0.0002

Data Index: 255862 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 1.2978. Min Range: -1.2978

Max Act: 1.1628. Min Act: -0.0001

Data Index: 1104125 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 1.2978. Min Range: -1.2978

Max Act: 1.1133. Min Act: -0.0001

Data Index: 562941 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 1.2978. Min Range: -1.2978

Max Act: 1.1177. Min Act: -0.0002

Data Index: 567047 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 1.2978. Min Range: -1.2978

Max Act: 1.1285. Min Act: -0.0002

Data Index: 513180 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 1.2978. Min Range: -1.2978

Max Act: 1.1418. Min Act: -0.0001

Data Index: 833469 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 1.2978. Min Range: -1.2978

Max Act: 1.0735. Min Act: -0.0002

Data Index: 1244762 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 1.2978. Min Range: -1.2978

Max Act: 1.0523. Min Act: -0.0002

Data Index: 92165 (C4 (Web Text))

Max Activating Token Index: 948

Text #15

Max Range: 1.2978. Min Range: -1.2978

Max Act: 1.0154. Min Act: -0.0001

Data Index: 770874 (C4 (Web Text))

Max Activating Token Index: 773

Text #16

Max Range: 1.2978. Min Range: -1.2978

Max Act: 1.0776. Min Act: -0.0001

Data Index: 824775 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 1.2978. Min Range: -1.2978

Max Act: 1.0916. Min Act: -0.0001

Data Index: 352227 (C4 (Web Text))

Max Activating Token Index: 382

Text #18

Max Range: 1.2978. Min Range: -1.2978

Max Act: 1.0666. Min Act: -0.0002

Data Index: 842813 (C4 (Web Text))

Max Activating Token Index: 977

Text #19

Max Range: 1.2978. Min Range: -1.2978

Max Act: 1.0654. Min Act: -0.0002

Data Index: 874581 (C4 (Web Text))

Max Activating Token Index: 812