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

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

Neuron 3697 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1355. Min Act: -0.0001

Data Index: 98027 (C4 (Web Text))

Max Activating Token Index: 709

Text #1

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1505. Min Act: -0.0001

Data Index: 179276 (C4 (Web Text))

Max Activating Token Index: 937

Text #2

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1047. Min Act: -0.0000

Data Index: 952339 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1294. Min Act: -0.0001

Data Index: 1089416 (C4 (Web Text))

Max Activating Token Index: 581

Text #4

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1140. Min Act: -0.0001

Data Index: 797843 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1137. Min Act: -0.0001

Data Index: 129063 (C4 (Web Text))

Max Activating Token Index: 852

Text #6

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1241. Min Act: -0.0001

Data Index: 1173352 (C4 (Web Text))

Max Activating Token Index: 351

Text #7

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.0962. Min Act: -0.0001

Data Index: 724525 (C4 (Web Text))

Max Activating Token Index: 678

Text #8

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1213. Min Act: -0.0001

Data Index: 725113 (C4 (Web Text))

Max Activating Token Index: 477

Text #9

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1000. Min Act: -0.0000

Data Index: 707261 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1074. Min Act: -0.0000

Data Index: 1171027 (C4 (Web Text))

Max Activating Token Index: 171

Text #11

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1082. Min Act: -0.0001

Data Index: 703905 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.0840. Min Act: -0.0000

Data Index: 1275939 (C4 (Web Text))

Max Activating Token Index: 890

Text #13

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.0960. Min Act: -0.0000

Data Index: 141770 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1039. Min Act: -0.0000

Data Index: 685758 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.0977. Min Act: -0.0000

Data Index: 1270228 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.0722. Min Act: -0.0000

Data Index: 409936 (C4 (Web Text))

Max Activating Token Index: 803

Text #17

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.0978. Min Act: -0.0000

Data Index: 148736 (C4 (Web Text))

Max Activating Token Index: 372

Text #18

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.0893. Min Act: -0.0000

Data Index: 702595 (C4 (Web Text))

Max Activating Token Index: 949

Text #19

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.0989. Min Act: -0.0001

Data Index: 585588 (C4 (Web Text))

Max Activating Token Index: 479