Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4393 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.4295. Min Range: -1.4295

Max Act: 1.4295. Min Act: -0.0002

Data Index: 515114 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 1.4295. Min Range: -1.4295

Max Act: 1.3114. Min Act: -0.0002

Data Index: 610937 (C4 (Web Text))

Max Activating Token Index: 192

Text #2

Max Range: 1.4295. Min Range: -1.4295

Max Act: 1.3315. Min Act: -0.0002

Data Index: 90789 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 1.4295. Min Range: -1.4295

Max Act: 1.3025. Min Act: -0.0002

Data Index: 771967 (C4 (Web Text))

Max Activating Token Index: 198

Text #4

Max Range: 1.4295. Min Range: -1.4295

Max Act: 1.3097. Min Act: -0.0002

Data Index: 768750 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 1.4295. Min Range: -1.4295

Max Act: 1.2970. Min Act: -0.0002

Data Index: 1024741 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 1.4295. Min Range: -1.4295

Max Act: 1.2921. Min Act: -0.0002

Data Index: 444749 (C4 (Web Text))

Max Activating Token Index: 131

Text #7

Max Range: 1.4295. Min Range: -1.4295

Max Act: 1.2836. Min Act: -0.0002

Data Index: 433712 (C4 (Web Text))

Max Activating Token Index: 213

Text #8

Max Range: 1.4295. Min Range: -1.4295

Max Act: 1.2839. Min Act: -0.0002

Data Index: 204520 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 1.4295. Min Range: -1.4295

Max Act: 1.2768. Min Act: -0.0002

Data Index: 19007 (C4 (Web Text))

Max Activating Token Index: 781

Text #10

Max Range: 1.4295. Min Range: -1.4295

Max Act: 1.3112. Min Act: -0.0002

Data Index: 634628 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 1.4295. Min Range: -1.4295

Max Act: 1.2583. Min Act: -0.0002

Data Index: 187265 (C4 (Web Text))

Max Activating Token Index: 184

Text #12

Max Range: 1.4295. Min Range: -1.4295

Max Act: 1.2535. Min Act: -0.0002

Data Index: 1310440 (C4 (Web Text))

Max Activating Token Index: 952

Text #13

Max Range: 1.4295. Min Range: -1.4295

Max Act: 1.2387. Min Act: -0.0002

Data Index: 890874 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 1.4295. Min Range: -1.4295

Max Act: 1.2442. Min Act: -0.0002

Data Index: 140103 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 1.4295. Min Range: -1.4295

Max Act: 1.2667. Min Act: -0.0002

Data Index: 871973 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 1.4295. Min Range: -1.4295

Max Act: 1.2473. Min Act: -0.0002

Data Index: 384995 (C4 (Web Text))

Max Activating Token Index: 48

Text #17

Max Range: 1.4295. Min Range: -1.4295

Max Act: 1.2629. Min Act: -0.0002

Data Index: 1290687 (C4 (Web Text))

Max Activating Token Index: 943

Text #18

Max Range: 1.4295. Min Range: -1.4295

Max Act: 1.2326. Min Act: -0.0002

Data Index: 203879 (C4 (Web Text))

Max Activating Token Index: 68

Text #19

Max Range: 1.4295. Min Range: -1.4295

Max Act: 1.2370. Min Act: -0.0002

Data Index: 836212 (C4 (Web Text))

Max Activating Token Index: 198