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

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

Neuron 4956 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: 0.9130. Min Range: -0.9130

Max Act: 0.9130. Min Act: -0.0002

Data Index: 1141615 (C4 (Web Text))

Max Activating Token Index: 739

Text #1

Max Range: 0.9130. Min Range: -0.9130

Max Act: 0.8708. Min Act: -0.0002

Data Index: 130303 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 0.9130. Min Range: -0.9130

Max Act: 0.8230. Min Act: -0.0002

Data Index: 731171 (C4 (Web Text))

Max Activating Token Index: 389

Text #3

Max Range: 0.9130. Min Range: -0.9130

Max Act: 0.8100. Min Act: -0.0002

Data Index: 781797 (C4 (Web Text))

Max Activating Token Index: 416

Text #4

Max Range: 0.9130. Min Range: -0.9130

Max Act: 0.8113. Min Act: -0.0002

Data Index: 1177239 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 0.9130. Min Range: -0.9130

Max Act: 0.7511. Min Act: -0.0002

Data Index: 1130497 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 0.9130. Min Range: -0.9130

Max Act: 0.7140. Min Act: -0.0002

Data Index: 826460 (C4 (Web Text))

Max Activating Token Index: 830

Text #7

Max Range: 0.9130. Min Range: -0.9130

Max Act: 0.6736. Min Act: -0.0002

Data Index: 822738 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 0.9130. Min Range: -0.9130

Max Act: 0.6533. Min Act: -0.0002

Data Index: 1159322 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 0.9130. Min Range: -0.9130

Max Act: 0.6468. Min Act: -0.0002

Data Index: 338344 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 0.9130. Min Range: -0.9130

Max Act: 0.6434. Min Act: -0.0002

Data Index: 688597 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 0.9130. Min Range: -0.9130

Max Act: 0.6226. Min Act: -0.0002

Data Index: 1040029 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 0.9130. Min Range: -0.9130

Max Act: 0.5813. Min Act: -0.0001

Data Index: 1083666 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 0.9130. Min Range: -0.9130

Max Act: 0.6181. Min Act: -0.0002

Data Index: 959614 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 0.9130. Min Range: -0.9130

Max Act: 0.6155. Min Act: -0.0002

Data Index: 32018 (C4 (Web Text))

Max Activating Token Index: 926

Text #15

Max Range: 0.9130. Min Range: -0.9130

Max Act: 0.5955. Min Act: -0.0002

Data Index: 512976 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 0.9130. Min Range: -0.9130

Max Act: 0.5482. Min Act: -0.0002

Data Index: 454166 (C4 (Web Text))

Max Activating Token Index: 865

Text #17

Max Range: 0.9130. Min Range: -0.9130

Max Act: 0.5638. Min Act: -0.0002

Data Index: 1249228 (C4 (Web Text))

Max Activating Token Index: 723

Text #18

Max Range: 0.9130. Min Range: -0.9130

Max Act: 0.5823. Min Act: -0.0002

Data Index: 867828 (C4 (Web Text))

Max Activating Token Index: 617

Text #19

Max Range: 0.9130. Min Range: -0.9130

Max Act: 0.5629. Min Act: -0.0002

Data Index: 1241962 (C4 (Web Text))

Max Activating Token Index: 122