Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1602 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.5072. Min Act: -0.0001

Data Index: 1219850 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.4777. Min Act: -0.0001

Data Index: 684478 (C4 (Web Text))

Max Activating Token Index: 373

Text #2

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.4432. Min Act: -0.0000

Data Index: 1229225 (C4 (Web Text))

Max Activating Token Index: 652

Text #3

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.4596. Min Act: -0.0000

Data Index: 367752 (C4 (Web Text))

Max Activating Token Index: 573

Text #4

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.4721. Min Act: -0.0001

Data Index: 470788 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.4374. Min Act: -0.0000

Data Index: 1044631 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.4159. Min Act: -0.0001

Data Index: 322660 (C4 (Web Text))

Max Activating Token Index: 881

Text #7

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.4420. Min Act: -0.0000

Data Index: 702994 (C4 (Web Text))

Max Activating Token Index: 68

Text #8

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.4365. Min Act: -0.0000

Data Index: 6655 (C4 (Web Text))

Max Activating Token Index: 873

Text #9

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.4220. Min Act: -0.0000

Data Index: 1048001 (C4 (Web Text))

Max Activating Token Index: 639

Text #10

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.4305. Min Act: -0.0000

Data Index: 48942 (C4 (Web Text))

Max Activating Token Index: 167

Text #11

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.4262. Min Act: -0.0000

Data Index: 40389 (C4 (Web Text))

Max Activating Token Index: 244

Text #12

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.4073. Min Act: -0.0000

Data Index: 648268 (C4 (Web Text))

Max Activating Token Index: 675

Text #13

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.4203. Min Act: -0.0000

Data Index: 898426 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.4194. Min Act: -0.0000

Data Index: 996093 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.4297. Min Act: -0.0001

Data Index: 1286762 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.3961. Min Act: -0.0000

Data Index: 808879 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.4056. Min Act: -0.0000

Data Index: 1252842 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.3827. Min Act: -0.0000

Data Index: 863014 (C4 (Web Text))

Max Activating Token Index: 811

Text #19

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.3902. Min Act: -0.0000

Data Index: 1235143 (C4 (Web Text))

Max Activating Token Index: 971