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

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

Neuron 5165 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1882. Min Range: -1.1882

Max Act: 1.1882. Min Act: -0.0000

Data Index: 658817 (C4 (Web Text))

Max Activating Token Index: 609

Text #1

Max Range: 1.1882. Min Range: -1.1882

Max Act: 0.9764. Min Act: -0.0000

Data Index: 565106 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 1.1882. Min Range: -1.1882

Max Act: 1.0397. Min Act: -0.0000

Data Index: 394086 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 1.1882. Min Range: -1.1882

Max Act: 0.9321. Min Act: -0.0000

Data Index: 68224 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 1.1882. Min Range: -1.1882

Max Act: 0.8798. Min Act: -0.0000

Data Index: 789809 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 1.1882. Min Range: -1.1882

Max Act: 0.8415. Min Act: -0.0000

Data Index: 672924 (C4 (Web Text))

Max Activating Token Index: 250

Text #6

Max Range: 1.1882. Min Range: -1.1882

Max Act: 0.8911. Min Act: -0.0000

Data Index: 1223818 (C4 (Web Text))

Max Activating Token Index: 982

Text #7

Max Range: 1.1882. Min Range: -1.1882

Max Act: 0.8350. Min Act: -0.0000

Data Index: 13160 (C4 (Web Text))

Max Activating Token Index: 400

Text #8

Max Range: 1.1882. Min Range: -1.1882

Max Act: 0.8222. Min Act: -0.0000

Data Index: 1080708 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 1.1882. Min Range: -1.1882

Max Act: 0.8111. Min Act: 0.0000

Data Index: 847032 (C4 (Web Text))

Max Activating Token Index: 846

Text #10

Max Range: 1.1882. Min Range: -1.1882

Max Act: 0.7663. Min Act: -0.0000

Data Index: 118615 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 1.1882. Min Range: -1.1882

Max Act: 0.7578. Min Act: -0.0000

Data Index: 1169976 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 1.1882. Min Range: -1.1882

Max Act: 0.8063. Min Act: -0.0000

Data Index: 385668 (C4 (Web Text))

Max Activating Token Index: 885

Text #13

Max Range: 1.1882. Min Range: -1.1882

Max Act: 0.7513. Min Act: -0.0000

Data Index: 292210 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 1.1882. Min Range: -1.1882

Max Act: 0.7953. Min Act: -0.0000

Data Index: 573458 (C4 (Web Text))

Max Activating Token Index: 753

Text #15

Max Range: 1.1882. Min Range: -1.1882

Max Act: 0.7439. Min Act: -0.0000

Data Index: 218532 (C4 (Web Text))

Max Activating Token Index: 158

Text #16

Max Range: 1.1882. Min Range: -1.1882

Max Act: 0.7906. Min Act: -0.0000

Data Index: 770297 (C4 (Web Text))

Max Activating Token Index: 546

Text #17

Max Range: 1.1882. Min Range: -1.1882

Max Act: 0.7752. Min Act: 0.0000

Data Index: 660223 (C4 (Web Text))

Max Activating Token Index: 965

Text #18

Max Range: 1.1882. Min Range: -1.1882

Max Act: 0.7569. Min Act: 0.0000

Data Index: 917380 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 1.1882. Min Range: -1.1882

Max Act: 0.7679. Min Act: -0.0000

Data Index: 537421 (C4 (Web Text))

Max Activating Token Index: 54