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

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

Neuron 2602 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.7191. Min Act: -0.0000

Data Index: 1114418 (C4 (Web Text))

Max Activating Token Index: 818

Text #1

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.8000. Min Act: -0.0000

Data Index: 1053595 (C4 (Web Text))

Max Activating Token Index: 668

Text #2

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.7092. Min Act: -0.0000

Data Index: 905075 (C4 (Web Text))

Max Activating Token Index: 972

Text #3

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.6994. Min Act: -0.0000

Data Index: 421174 (C4 (Web Text))

Max Activating Token Index: 118

Text #4

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.7491. Min Act: -0.0000

Data Index: 1011101 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.7256. Min Act: -0.0000

Data Index: 215262 (C4 (Web Text))

Max Activating Token Index: 609

Text #6

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.6852. Min Act: -0.0000

Data Index: 742160 (C4 (Web Text))

Max Activating Token Index: 187

Text #7

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.6124. Min Act: -0.0000

Data Index: 341930 (C4 (Web Text))

Max Activating Token Index: 1011

Text #8

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.6264. Min Act: -0.0000

Data Index: 1017217 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.6185. Min Act: -0.0000

Data Index: 597825 (C4 (Web Text))

Max Activating Token Index: 211

Text #10

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.5902. Min Act: -0.0000

Data Index: 909227 (C4 (Web Text))

Max Activating Token Index: 53

Text #11

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.5910. Min Act: -0.0000

Data Index: 631402 (C4 (Web Text))

Max Activating Token Index: 902

Text #12

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.6074. Min Act: -0.0000

Data Index: 542735 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.5485. Min Act: -0.0000

Data Index: 248091 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.5880. Min Act: -0.0000

Data Index: 715421 (C4 (Web Text))

Max Activating Token Index: 580

Text #15

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.6210. Min Act: -0.0000

Data Index: 760911 (C4 (Web Text))

Max Activating Token Index: 1003

Text #16

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.5842. Min Act: -0.0000

Data Index: 1169509 (C4 (Web Text))

Max Activating Token Index: 555

Text #17

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.5302. Min Act: -0.0000

Data Index: 1305276 (C4 (Web Text))

Max Activating Token Index: 860

Text #18

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.5951. Min Act: -0.0000

Data Index: 430957 (C4 (Web Text))

Max Activating Token Index: 519

Text #19

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.6395. Min Act: -0.0000

Data Index: 516109 (C4 (Web Text))

Max Activating Token Index: 1009