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

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

Neuron 388 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.1581. Min Act: -0.0002

Data Index: 1190785 (C4 (Web Text))

Max Activating Token Index: 409

Text #1

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.1060. Min Act: -0.0002

Data Index: 1294041 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.0975. Min Act: -0.0002

Data Index: 681752 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.0887. Min Act: -0.0002

Data Index: 176400 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.0947. Min Act: -0.0002

Data Index: 256608 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.0977. Min Act: -0.0002

Data Index: 542504 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.0939. Min Act: -0.0002

Data Index: 266714 (C4 (Web Text))

Max Activating Token Index: 487

Text #7

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.0976. Min Act: -0.0002

Data Index: 410952 (C4 (Web Text))

Max Activating Token Index: 115

Text #8

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.0863. Min Act: -0.0002

Data Index: 276161 (C4 (Web Text))

Max Activating Token Index: 160

Text #9

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.0879. Min Act: -0.0002

Data Index: 707736 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.0904. Min Act: -0.0002

Data Index: 937770 (C4 (Web Text))

Max Activating Token Index: 575

Text #11

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.0825. Min Act: -0.0002

Data Index: 1325585 (C4 (Web Text))

Max Activating Token Index: 297

Text #12

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.0829. Min Act: -0.0002

Data Index: 1197989 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.0872. Min Act: -0.0002

Data Index: 118259 (C4 (Web Text))

Max Activating Token Index: 211

Text #14

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.0815. Min Act: -0.0002

Data Index: 696751 (C4 (Web Text))

Max Activating Token Index: 189

Text #15

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.0812. Min Act: -0.0002

Data Index: 615562 (C4 (Web Text))

Max Activating Token Index: 964

Text #16

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.0792. Min Act: -0.0002

Data Index: 1209202 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.0793. Min Act: -0.0002

Data Index: 969507 (C4 (Web Text))

Max Activating Token Index: 566

Text #18

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.0836. Min Act: -0.0002

Data Index: 543066 (C4 (Web Text))

Max Activating Token Index: 594

Text #19

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.0758. Min Act: -0.0002

Data Index: 1117674 (C4 (Web Text))

Max Activating Token Index: 95