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

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

Neuron 2361 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.3088. Min Act: -0.0001

Data Index: 1149928 (C4 (Web Text))

Max Activating Token Index: 765

Text #1

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.2947. Min Act: -0.0001

Data Index: 216186 (C4 (Web Text))

Max Activating Token Index: 290

Text #2

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.3567. Min Act: -0.0001

Data Index: 920555 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.3138. Min Act: -0.0001

Data Index: 375720 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.1568. Min Act: -0.0001

Data Index: 546735 (C4 (Web Text))

Max Activating Token Index: 825

Text #5

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.2438. Min Act: -0.0001

Data Index: 6334 (C4 (Web Text))

Max Activating Token Index: 814

Text #6

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.1010. Min Act: -0.0001

Data Index: 1178224 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.1245. Min Act: -0.0001

Data Index: 648732 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.0481. Min Act: -0.0001

Data Index: 997906 (C4 (Web Text))

Max Activating Token Index: 567

Text #9

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.0427. Min Act: -0.0001

Data Index: 1088170 (C4 (Web Text))

Max Activating Token Index: 781

Text #10

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.1171. Min Act: -0.0001

Data Index: 801330 (C4 (Web Text))

Max Activating Token Index: 754

Text #11

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.0600. Min Act: -0.0001

Data Index: 578988 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.0057. Min Act: -0.0001

Data Index: 607697 (C4 (Web Text))

Max Activating Token Index: 542

Text #13

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.1486. Min Act: -0.0001

Data Index: 819608 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.0234. Min Act: -0.0001

Data Index: 235122 (C4 (Web Text))

Max Activating Token Index: 504

Text #15

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.0877. Min Act: -0.0001

Data Index: 730214 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.1085. Min Act: -0.0001

Data Index: 1071302 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.0074. Min Act: -0.0001

Data Index: 1166692 (C4 (Web Text))

Max Activating Token Index: 765

Text #18

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.0367. Min Act: -0.0001

Data Index: 1025882 (C4 (Web Text))

Max Activating Token Index: 657

Text #19

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.0246. Min Act: -0.0001

Data Index: 927574 (C4 (Web Text))

Max Activating Token Index: 622