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

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

Neuron 3480 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5809. Min Range: -2.5809

Max Act: 2.3338. Min Act: -0.0001

Data Index: 55660 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 2.5809. Min Range: -2.5809

Max Act: 2.5809. Min Act: -0.0001

Data Index: 1149583 (C4 (Web Text))

Max Activating Token Index: 904

Text #2

Max Range: 2.5809. Min Range: -2.5809

Max Act: 2.2042. Min Act: -0.0001

Data Index: 1322690 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 2.5809. Min Range: -2.5809

Max Act: 2.2781. Min Act: -0.0000

Data Index: 1085536 (C4 (Web Text))

Max Activating Token Index: 283

Text #4

Max Range: 2.5809. Min Range: -2.5809

Max Act: 2.4489. Min Act: -0.0000

Data Index: 479463 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 2.5809. Min Range: -2.5809

Max Act: 2.0811. Min Act: -0.0001

Data Index: 651111 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 2.5809. Min Range: -2.5809

Max Act: 1.8943. Min Act: -0.0001

Data Index: 153750 (C4 (Web Text))

Max Activating Token Index: 452

Text #7

Max Range: 2.5809. Min Range: -2.5809

Max Act: 1.9745. Min Act: -0.0000

Data Index: 192205 (C4 (Web Text))

Max Activating Token Index: 393

Text #8

Max Range: 2.5809. Min Range: -2.5809

Max Act: 1.8995. Min Act: -0.0001

Data Index: 1316597 (C4 (Web Text))

Max Activating Token Index: 637

Text #9

Max Range: 2.5809. Min Range: -2.5809

Max Act: 2.2113. Min Act: -0.0001

Data Index: 848766 (C4 (Web Text))

Max Activating Token Index: 404

Text #10

Max Range: 2.5809. Min Range: -2.5809

Max Act: 2.2007. Min Act: -0.0001

Data Index: 6680 (C4 (Web Text))

Max Activating Token Index: 364

Text #11

Max Range: 2.5809. Min Range: -2.5809

Max Act: 1.8604. Min Act: -0.0000

Data Index: 806930 (C4 (Web Text))

Max Activating Token Index: 938

Text #12

Max Range: 2.5809. Min Range: -2.5809

Max Act: 2.0956. Min Act: -0.0000

Data Index: 67905 (C4 (Web Text))

Max Activating Token Index: 352

Text #13

Max Range: 2.5809. Min Range: -2.5809

Max Act: 1.7627. Min Act: -0.0000

Data Index: 91767 (C4 (Web Text))

Max Activating Token Index: 83

Text #14

Max Range: 2.5809. Min Range: -2.5809

Max Act: 1.8468. Min Act: -0.0000

Data Index: 1238132 (C4 (Web Text))

Max Activating Token Index: 271

Text #15

Max Range: 2.5809. Min Range: -2.5809

Max Act: 1.8796. Min Act: -0.0001

Data Index: 742568 (C4 (Web Text))

Max Activating Token Index: 952

Text #16

Max Range: 2.5809. Min Range: -2.5809

Max Act: 1.8990. Min Act: -0.0000

Data Index: 743456 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 2.5809. Min Range: -2.5809

Max Act: 1.8677. Min Act: -0.0000

Data Index: 1298020 (C4 (Web Text))

Max Activating Token Index: 729

Text #18

Max Range: 2.5809. Min Range: -2.5809

Max Act: 1.6104. Min Act: -0.0000

Data Index: 601174 (C4 (Web Text))

Max Activating Token Index: 298

Text #19

Max Range: 2.5809. Min Range: -2.5809

Max Act: 1.7219. Min Act: -0.0001

Data Index: 110633 (C4 (Web Text))

Max Activating Token Index: 122