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

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

Neuron 4912 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: 1.1222. Min Range: -1.1222

Max Act: 1.1222. Min Act: -0.0000

Data Index: 564288 (C4 (Web Text))

Max Activating Token Index: 276

Text #1

Max Range: 1.1222. Min Range: -1.1222

Max Act: 1.0217. Min Act: -0.0000

Data Index: 331133 (C4 (Web Text))

Max Activating Token Index: 567

Text #2

Max Range: 1.1222. Min Range: -1.1222

Max Act: 1.0029. Min Act: -0.0000

Data Index: 1327468 (C4 (Web Text))

Max Activating Token Index: 558

Text #3

Max Range: 1.1222. Min Range: -1.1222

Max Act: 1.0375. Min Act: -0.0000

Data Index: 973500 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 1.1222. Min Range: -1.1222

Max Act: 0.9758. Min Act: -0.0000

Data Index: 830617 (C4 (Web Text))

Max Activating Token Index: 417

Text #5

Max Range: 1.1222. Min Range: -1.1222

Max Act: 0.9195. Min Act: -0.0000

Data Index: 257341 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 1.1222. Min Range: -1.1222

Max Act: 0.8656. Min Act: -0.0000

Data Index: 559858 (C4 (Web Text))

Max Activating Token Index: 737

Text #7

Max Range: 1.1222. Min Range: -1.1222

Max Act: 0.8892. Min Act: -0.0000

Data Index: 1034510 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 1.1222. Min Range: -1.1222

Max Act: 0.8549. Min Act: -0.0000

Data Index: 854727 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 1.1222. Min Range: -1.1222

Max Act: 0.8754. Min Act: -0.0000

Data Index: 728099 (C4 (Web Text))

Max Activating Token Index: 558

Text #10

Max Range: 1.1222. Min Range: -1.1222

Max Act: 0.8757. Min Act: -0.0000

Data Index: 1237153 (C4 (Web Text))

Max Activating Token Index: 799

Text #11

Max Range: 1.1222. Min Range: -1.1222

Max Act: 0.8706. Min Act: -0.0000

Data Index: 1008854 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 1.1222. Min Range: -1.1222

Max Act: 0.8643. Min Act: -0.0000

Data Index: 405434 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 1.1222. Min Range: -1.1222

Max Act: 0.8401. Min Act: -0.0000

Data Index: 1336146 (C4 (Web Text))

Max Activating Token Index: 524

Text #14

Max Range: 1.1222. Min Range: -1.1222

Max Act: 0.8354. Min Act: -0.0000

Data Index: 547727 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 1.1222. Min Range: -1.1222

Max Act: 0.8536. Min Act: -0.0000

Data Index: 789068 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 1.1222. Min Range: -1.1222

Max Act: 0.8775. Min Act: -0.0000

Data Index: 334855 (C4 (Web Text))

Max Activating Token Index: 680

Text #17

Max Range: 1.1222. Min Range: -1.1222

Max Act: 0.7941. Min Act: -0.0000

Data Index: 143863 (C4 (Web Text))

Max Activating Token Index: 341

Text #18

Max Range: 1.1222. Min Range: -1.1222

Max Act: 0.8402. Min Act: -0.0000

Data Index: 383313 (C4 (Web Text))

Max Activating Token Index: 906

Text #19

Max Range: 1.1222. Min Range: -1.1222

Max Act: 0.8654. Min Act: -0.0000

Data Index: 1298612 (C4 (Web Text))

Max Activating Token Index: 42