Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1841 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1685. Min Act: -0.0000

Data Index: 129237 (C4 (Web Text))

Max Activating Token Index: 398

Text #1

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1367. Min Act: -0.0000

Data Index: 1314498 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1190. Min Act: -0.0000

Data Index: 1248047 (C4 (Web Text))

Max Activating Token Index: 565

Text #3

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1057. Min Act: -0.0000

Data Index: 301159 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1045. Min Act: -0.0000

Data Index: 512857 (C4 (Web Text))

Max Activating Token Index: 349

Text #5

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1106. Min Act: -0.0000

Data Index: 147792 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1063. Min Act: -0.0000

Data Index: 949366 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.0983. Min Act: -0.0000

Data Index: 836814 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.0884. Min Act: -0.0000

Data Index: 441355 (C4 (Web Text))

Max Activating Token Index: 739

Text #9

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.0926. Min Act: -0.0000

Data Index: 994193 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.0968. Min Act: -0.0000

Data Index: 264696 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.0957. Min Act: -0.0000

Data Index: 1027467 (C4 (Web Text))

Max Activating Token Index: 232

Text #12

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.0962. Min Act: -0.0000

Data Index: 913209 (C4 (Web Text))

Max Activating Token Index: 801

Text #13

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.0989. Min Act: -0.0000

Data Index: 475225 (C4 (Web Text))

Max Activating Token Index: 728

Text #14

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.0978. Min Act: -0.0000

Data Index: 782249 (C4 (Web Text))

Max Activating Token Index: 510

Text #15

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.0905. Min Act: -0.0000

Data Index: 66595 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.0993. Min Act: -0.0000

Data Index: 1042465 (C4 (Web Text))

Max Activating Token Index: 775

Text #17

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.0932. Min Act: -0.0000

Data Index: 869011 (C4 (Web Text))

Max Activating Token Index: 511

Text #18

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.0886. Min Act: -0.0000

Data Index: 1082528 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.0914. Min Act: -0.0000

Data Index: 907005 (C4 (Web Text))

Max Activating Token Index: 739