Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1799 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1159. Min Act: -0.0003

Data Index: 257596 (C4 (Web Text))

Max Activating Token Index: 524

Text #1

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1212. Min Act: -0.0003

Data Index: 1033155 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1097. Min Act: -0.0003

Data Index: 832730 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1071. Min Act: -0.0003

Data Index: 750334 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1025. Min Act: -0.0003

Data Index: 681459 (C4 (Web Text))

Max Activating Token Index: 622

Text #5

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1015. Min Act: -0.0003

Data Index: 743382 (C4 (Web Text))

Max Activating Token Index: 511

Text #6

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1011. Min Act: -0.0003

Data Index: 1117135 (C4 (Web Text))

Max Activating Token Index: 375

Text #7

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1022. Min Act: -0.0003

Data Index: 993124 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0999. Min Act: -0.0003

Data Index: 849445 (C4 (Web Text))

Max Activating Token Index: 449

Text #9

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1031. Min Act: -0.0003

Data Index: 387105 (C4 (Web Text))

Max Activating Token Index: 367

Text #10

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1008. Min Act: -0.0003

Data Index: 882028 (C4 (Web Text))

Max Activating Token Index: 629

Text #11

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1032. Min Act: -0.0003

Data Index: 299136 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0993. Min Act: -0.0003

Data Index: 783722 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1056. Min Act: -0.0003

Data Index: 399847 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1037. Min Act: -0.0003

Data Index: 7617 (C4 (Web Text))

Max Activating Token Index: 613

Text #15

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1035. Min Act: -0.0003

Data Index: 1268050 (C4 (Web Text))

Max Activating Token Index: 243

Text #16

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0984. Min Act: -0.0003

Data Index: 961558 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0969. Min Act: -0.0003

Data Index: 280481 (C4 (Web Text))

Max Activating Token Index: 809

Text #18

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0972. Min Act: -0.0003

Data Index: 308770 (C4 (Web Text))

Max Activating Token Index: 384

Text #19

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1014. Min Act: -0.0003

Data Index: 579 (C4 (Web Text))

Max Activating Token Index: 68