Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 807 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.5709. Min Range: -1.5709

Max Act: 1.5709. Min Act: -0.0001

Data Index: 864026 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 1.5709. Min Range: -1.5709

Max Act: 1.3076. Min Act: -0.0001

Data Index: 618991 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 1.5709. Min Range: -1.5709

Max Act: 1.1149. Min Act: -0.0001

Data Index: 891643 (C4 (Web Text))

Max Activating Token Index: 875

Text #3

Max Range: 1.5709. Min Range: -1.5709

Max Act: 1.0497. Min Act: -0.0001

Data Index: 1012584 (C4 (Web Text))

Max Activating Token Index: 877

Text #4

Max Range: 1.5709. Min Range: -1.5709

Max Act: 1.0690. Min Act: -0.0001

Data Index: 411770 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 1.5709. Min Range: -1.5709

Max Act: 1.0691. Min Act: -0.0001

Data Index: 646521 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 1.5709. Min Range: -1.5709

Max Act: 0.9831. Min Act: -0.0001

Data Index: 273156 (C4 (Web Text))

Max Activating Token Index: 198

Text #7

Max Range: 1.5709. Min Range: -1.5709

Max Act: 0.9625. Min Act: -0.0001

Data Index: 826852 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 1.5709. Min Range: -1.5709

Max Act: 0.9247. Min Act: -0.0001

Data Index: 1162750 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 1.5709. Min Range: -1.5709

Max Act: 0.9532. Min Act: -0.0001

Data Index: 60579 (C4 (Web Text))

Max Activating Token Index: 810

Text #10

Max Range: 1.5709. Min Range: -1.5709

Max Act: 0.9059. Min Act: -0.0001

Data Index: 399037 (C4 (Web Text))

Max Activating Token Index: 1008

Text #11

Max Range: 1.5709. Min Range: -1.5709

Max Act: 1.0023. Min Act: -0.0001

Data Index: 1332868 (C4 (Web Text))

Max Activating Token Index: 305

Text #12

Max Range: 1.5709. Min Range: -1.5709

Max Act: 0.9544. Min Act: -0.0001

Data Index: 1210649 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 1.5709. Min Range: -1.5709

Max Act: 0.9574. Min Act: -0.0001

Data Index: 300572 (C4 (Web Text))

Max Activating Token Index: 964

Text #14

Max Range: 1.5709. Min Range: -1.5709

Max Act: 0.9201. Min Act: -0.0001

Data Index: 214697 (C4 (Web Text))

Max Activating Token Index: 134

Text #15

Max Range: 1.5709. Min Range: -1.5709

Max Act: 0.9236. Min Act: -0.0001

Data Index: 641838 (C4 (Web Text))

Max Activating Token Index: 1010

Text #16

Max Range: 1.5709. Min Range: -1.5709

Max Act: 0.8686. Min Act: -0.0001

Data Index: 1143213 (C4 (Web Text))

Max Activating Token Index: 668

Text #17

Max Range: 1.5709. Min Range: -1.5709

Max Act: 0.9421. Min Act: -0.0001

Data Index: 1197524 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 1.5709. Min Range: -1.5709

Max Act: 0.8854. Min Act: -0.0001

Data Index: 904364 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 1.5709. Min Range: -1.5709

Max Act: 0.8806. Min Act: -0.0001

Data Index: 729061 (C4 (Web Text))

Max Activating Token Index: 47