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

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

Neuron 4638 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: 1.4654. Min Range: -1.4654

Max Act: 1.4585. Min Act: -0.0000

Data Index: 308824 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 1.4654. Min Range: -1.4654

Max Act: 1.4092. Min Act: -0.0000

Data Index: 1009482 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 1.4654. Min Range: -1.4654

Max Act: 1.4654. Min Act: -0.0000

Data Index: 794116 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 1.4654. Min Range: -1.4654

Max Act: 1.3156. Min Act: -0.0000

Data Index: 1353565 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 1.4654. Min Range: -1.4654

Max Act: 1.3102. Min Act: -0.0000

Data Index: 268840 (C4 (Web Text))

Max Activating Token Index: 703

Text #5

Max Range: 1.4654. Min Range: -1.4654

Max Act: 1.2892. Min Act: -0.0000

Data Index: 117205 (C4 (Web Text))

Max Activating Token Index: 799

Text #6

Max Range: 1.4654. Min Range: -1.4654

Max Act: 1.3193. Min Act: -0.0000

Data Index: 877207 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 1.4654. Min Range: -1.4654

Max Act: 1.2770. Min Act: -0.0000

Data Index: 54485 (C4 (Web Text))

Max Activating Token Index: 48

Text #8

Max Range: 1.4654. Min Range: -1.4654

Max Act: 1.3769. Min Act: -0.0000

Data Index: 430652 (C4 (Web Text))

Max Activating Token Index: 205

Text #9

Max Range: 1.4654. Min Range: -1.4654

Max Act: 1.3251. Min Act: -0.0000

Data Index: 74634 (C4 (Web Text))

Max Activating Token Index: 635

Text #10

Max Range: 1.4654. Min Range: -1.4654

Max Act: 1.2141. Min Act: -0.0000

Data Index: 392969 (C4 (Web Text))

Max Activating Token Index: 266

Text #11

Max Range: 1.4654. Min Range: -1.4654

Max Act: 1.3202. Min Act: -0.0000

Data Index: 1222081 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 1.4654. Min Range: -1.4654

Max Act: 1.2190. Min Act: -0.0000

Data Index: 218577 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 1.4654. Min Range: -1.4654

Max Act: 1.2471. Min Act: -0.0000

Data Index: 304844 (C4 (Web Text))

Max Activating Token Index: 848

Text #14

Max Range: 1.4654. Min Range: -1.4654

Max Act: 1.2576. Min Act: -0.0000

Data Index: 977496 (C4 (Web Text))

Max Activating Token Index: 258

Text #15

Max Range: 1.4654. Min Range: -1.4654

Max Act: 1.2557. Min Act: -0.0000

Data Index: 1065605 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 1.4654. Min Range: -1.4654

Max Act: 1.2257. Min Act: -0.0000

Data Index: 1323000 (C4 (Web Text))

Max Activating Token Index: 783

Text #17

Max Range: 1.4654. Min Range: -1.4654

Max Act: 1.2770. Min Act: -0.0000

Data Index: 890890 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 1.4654. Min Range: -1.4654

Max Act: 1.1924. Min Act: -0.0000

Data Index: 1132807 (C4 (Web Text))

Max Activating Token Index: 197

Text #19

Max Range: 1.4654. Min Range: -1.4654

Max Act: 1.1799. Min Act: -0.0000

Data Index: 1037460 (C4 (Web Text))

Max Activating Token Index: 226