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

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

Neuron 3163 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1219. Min Act: -0.0002

Data Index: 940566 (C4 (Web Text))

Max Activating Token Index: 716

Text #1

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1003. Min Act: -0.0002

Data Index: 512045 (C4 (Web Text))

Max Activating Token Index: 79

Text #2

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0994. Min Act: -0.0002

Data Index: 1509860 (Python Code)

Max Activating Token Index: 131

Text #3

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0992. Min Act: -0.0002

Data Index: 313283 (C4 (Web Text))

Max Activating Token Index: 692

Text #4

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0977. Min Act: -0.0002

Data Index: 1455273 (Python Code)

Max Activating Token Index: 130

Text #5

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0968. Min Act: -0.0002

Data Index: 666418 (C4 (Web Text))

Max Activating Token Index: 192

Text #6

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0953. Min Act: -0.0002

Data Index: 1021726 (C4 (Web Text))

Max Activating Token Index: 302

Text #7

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0920. Min Act: -0.0002

Data Index: 119632 (C4 (Web Text))

Max Activating Token Index: 135

Text #8

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0899. Min Act: -0.0002

Data Index: 286454 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0965. Min Act: -0.0002

Data Index: 146676 (C4 (Web Text))

Max Activating Token Index: 446

Text #10

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0886. Min Act: -0.0002

Data Index: 1264713 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0911. Min Act: -0.0002

Data Index: 953734 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0916. Min Act: -0.0002

Data Index: 222569 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0896. Min Act: -0.0002

Data Index: 1242558 (C4 (Web Text))

Max Activating Token Index: 289

Text #14

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0935. Min Act: -0.0002

Data Index: 985442 (C4 (Web Text))

Max Activating Token Index: 991

Text #15

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0938. Min Act: -0.0002

Data Index: 907433 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0850. Min Act: -0.0002

Data Index: 450814 (C4 (Web Text))

Max Activating Token Index: 521

Text #17

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0912. Min Act: -0.0002

Data Index: 904209 (C4 (Web Text))

Max Activating Token Index: 634

Text #18

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0858. Min Act: -0.0002

Data Index: 473406 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0872. Min Act: -0.0002

Data Index: 773748 (C4 (Web Text))

Max Activating Token Index: 644