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

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

Neuron 306 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: 1.7902. Min Range: -1.7902

Max Act: 1.7902. Min Act: -0.0001

Data Index: 1213300 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 1.7902. Min Range: -1.7902

Max Act: 1.7536. Min Act: -0.0001

Data Index: 192232 (C4 (Web Text))

Max Activating Token Index: 905

Text #2

Max Range: 1.7902. Min Range: -1.7902

Max Act: 1.7304. Min Act: -0.0001

Data Index: 374551 (C4 (Web Text))

Max Activating Token Index: 157

Text #3

Max Range: 1.7902. Min Range: -1.7902

Max Act: 1.6378. Min Act: -0.0001

Data Index: 1137510 (C4 (Web Text))

Max Activating Token Index: 306

Text #4

Max Range: 1.7902. Min Range: -1.7902

Max Act: 1.5456. Min Act: -0.0001

Data Index: 795874 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 1.7902. Min Range: -1.7902

Max Act: 1.5868. Min Act: -0.0001

Data Index: 1315223 (C4 (Web Text))

Max Activating Token Index: 857

Text #6

Max Range: 1.7902. Min Range: -1.7902

Max Act: 1.6052. Min Act: -0.0001

Data Index: 653844 (C4 (Web Text))

Max Activating Token Index: 903

Text #7

Max Range: 1.7902. Min Range: -1.7902

Max Act: 1.5988. Min Act: -0.0001

Data Index: 805854 (C4 (Web Text))

Max Activating Token Index: 669

Text #8

Max Range: 1.7902. Min Range: -1.7902

Max Act: 1.5468. Min Act: -0.0001

Data Index: 882203 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 1.7902. Min Range: -1.7902

Max Act: 1.4224. Min Act: -0.0001

Data Index: 249726 (C4 (Web Text))

Max Activating Token Index: 983

Text #10

Max Range: 1.7902. Min Range: -1.7902

Max Act: 1.4661. Min Act: -0.0001

Data Index: 837617 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 1.7902. Min Range: -1.7902

Max Act: 1.5085. Min Act: -0.0001

Data Index: 1180187 (C4 (Web Text))

Max Activating Token Index: 109

Text #12

Max Range: 1.7902. Min Range: -1.7902

Max Act: 1.5576. Min Act: -0.0001

Data Index: 1310606 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 1.7902. Min Range: -1.7902

Max Act: 1.5021. Min Act: -0.0001

Data Index: 1779 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 1.7902. Min Range: -1.7902

Max Act: 1.5234. Min Act: -0.0001

Data Index: 582306 (C4 (Web Text))

Max Activating Token Index: 845

Text #15

Max Range: 1.7902. Min Range: -1.7902

Max Act: 1.4264. Min Act: -0.0001

Data Index: 544864 (C4 (Web Text))

Max Activating Token Index: 937

Text #16

Max Range: 1.7902. Min Range: -1.7902

Max Act: 1.4511. Min Act: -0.0001

Data Index: 405120 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 1.7902. Min Range: -1.7902

Max Act: 1.5230. Min Act: -0.0001

Data Index: 1316614 (C4 (Web Text))

Max Activating Token Index: 673

Text #18

Max Range: 1.7902. Min Range: -1.7902

Max Act: 1.4912. Min Act: -0.0001

Data Index: 614532 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 1.7902. Min Range: -1.7902

Max Act: 1.4056. Min Act: -0.0001

Data Index: 413778 (C4 (Web Text))

Max Activating Token Index: 938