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

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

Neuron 3083 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1222. Min Act: -0.0001

Data Index: 997703 (C4 (Web Text))

Max Activating Token Index: 793

Text #1

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1164. Min Act: -0.0001

Data Index: 1166674 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1110. Min Act: -0.0000

Data Index: 1136481 (C4 (Web Text))

Max Activating Token Index: 185

Text #3

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1032. Min Act: -0.0000

Data Index: 306123 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1147. Min Act: -0.0001

Data Index: 1116509 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0981. Min Act: -0.0001

Data Index: 1043018 (C4 (Web Text))

Max Activating Token Index: 643

Text #6

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0994. Min Act: -0.0001

Data Index: 116927 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0909. Min Act: -0.0000

Data Index: 132549 (C4 (Web Text))

Max Activating Token Index: 621

Text #8

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0925. Min Act: -0.0000

Data Index: 1019319 (C4 (Web Text))

Max Activating Token Index: 561

Text #9

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0951. Min Act: -0.0001

Data Index: 501334 (C4 (Web Text))

Max Activating Token Index: 965

Text #10

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0985. Min Act: -0.0000

Data Index: 179910 (C4 (Web Text))

Max Activating Token Index: 135

Text #11

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0908. Min Act: -0.0001

Data Index: 702965 (C4 (Web Text))

Max Activating Token Index: 519

Text #12

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0892. Min Act: -0.0000

Data Index: 1206848 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0921. Min Act: -0.0000

Data Index: 1337366 (C4 (Web Text))

Max Activating Token Index: 861

Text #14

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0917. Min Act: -0.0001

Data Index: 1206832 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0939. Min Act: -0.0001

Data Index: 555428 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0902. Min Act: -0.0000

Data Index: 585652 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0926. Min Act: -0.0001

Data Index: 626989 (C4 (Web Text))

Max Activating Token Index: 379

Text #18

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0890. Min Act: -0.0001

Data Index: 1096725 (C4 (Web Text))

Max Activating Token Index: 122

Text #19

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0889. Min Act: -0.0000

Data Index: 312905 (C4 (Web Text))

Max Activating Token Index: 842