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

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

Neuron 1737 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3889. Min Range: -1.3889

Max Act: 1.3889. Min Act: -0.0001

Data Index: 1178184 (C4 (Web Text))

Max Activating Token Index: 937

Text #1

Max Range: 1.3889. Min Range: -1.3889

Max Act: 1.3587. Min Act: -0.0001

Data Index: 897723 (C4 (Web Text))

Max Activating Token Index: 1022

Text #2

Max Range: 1.3889. Min Range: -1.3889

Max Act: 1.2227. Min Act: -0.0001

Data Index: 626046 (C4 (Web Text))

Max Activating Token Index: 500

Text #3

Max Range: 1.3889. Min Range: -1.3889

Max Act: 1.2456. Min Act: -0.0001

Data Index: 1081414 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 1.3889. Min Range: -1.3889

Max Act: 1.1954. Min Act: -0.0001

Data Index: 89803 (C4 (Web Text))

Max Activating Token Index: 1011

Text #5

Max Range: 1.3889. Min Range: -1.3889

Max Act: 1.1537. Min Act: -0.0001

Data Index: 1038382 (C4 (Web Text))

Max Activating Token Index: 1001

Text #6

Max Range: 1.3889. Min Range: -1.3889

Max Act: 1.1506. Min Act: -0.0001

Data Index: 757853 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 1.3889. Min Range: -1.3889

Max Act: 1.1434. Min Act: -0.0001

Data Index: 252623 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 1.3889. Min Range: -1.3889

Max Act: 1.1303. Min Act: -0.0001

Data Index: 1354582 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 1.3889. Min Range: -1.3889

Max Act: 1.1408. Min Act: -0.0001

Data Index: 5180 (C4 (Web Text))

Max Activating Token Index: 20

Text #10

Max Range: 1.3889. Min Range: -1.3889

Max Act: 1.0952. Min Act: -0.0001

Data Index: 506220 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 1.3889. Min Range: -1.3889

Max Act: 1.1158. Min Act: -0.0001

Data Index: 789662 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 1.3889. Min Range: -1.3889

Max Act: 1.1565. Min Act: -0.0001

Data Index: 1031584 (C4 (Web Text))

Max Activating Token Index: 270

Text #13

Max Range: 1.3889. Min Range: -1.3889

Max Act: 1.0587. Min Act: -0.0001

Data Index: 827706 (C4 (Web Text))

Max Activating Token Index: 324

Text #14

Max Range: 1.3889. Min Range: -1.3889

Max Act: 1.0960. Min Act: -0.0001

Data Index: 150107 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 1.3889. Min Range: -1.3889

Max Act: 1.0904. Min Act: -0.0001

Data Index: 235991 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 1.3889. Min Range: -1.3889

Max Act: 1.1194. Min Act: -0.0001

Data Index: 35408 (C4 (Web Text))

Max Activating Token Index: 489

Text #17

Max Range: 1.3889. Min Range: -1.3889

Max Act: 1.0894. Min Act: -0.0001

Data Index: 141683 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 1.3889. Min Range: -1.3889

Max Act: 1.0722. Min Act: -0.0001

Data Index: 207823 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 1.3889. Min Range: -1.3889

Max Act: 1.0982. Min Act: -0.0001

Data Index: 253835 (C4 (Web Text))

Max Activating Token Index: 594