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

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

Neuron 3202 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: 0.1045. Min Range: -0.1045

Max Act: 0.1045. Min Act: -0.0000

Data Index: 549716 (C4 (Web Text))

Max Activating Token Index: 965

Text #1

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.1034. Min Act: -0.0000

Data Index: 622842 (C4 (Web Text))

Max Activating Token Index: 677

Text #2

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0998. Min Act: -0.0000

Data Index: 50507 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0950. Min Act: -0.0001

Data Index: 1000192 (C4 (Web Text))

Max Activating Token Index: 136

Text #4

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0964. Min Act: -0.0001

Data Index: 249616 (C4 (Web Text))

Max Activating Token Index: 668

Text #5

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0902. Min Act: -0.0001

Data Index: 321166 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0895. Min Act: -0.0000

Data Index: 354226 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0950. Min Act: -0.0001

Data Index: 200217 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0897. Min Act: -0.0001

Data Index: 558149 (C4 (Web Text))

Max Activating Token Index: 456

Text #9

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0884. Min Act: -0.0000

Data Index: 1357213 (C4 (Web Text))

Max Activating Token Index: 934

Text #10

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0886. Min Act: -0.0001

Data Index: 4933 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0880. Min Act: -0.0001

Data Index: 659475 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0911. Min Act: -0.0001

Data Index: 1022147 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0841. Min Act: -0.0001

Data Index: 158470 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0868. Min Act: -0.0000

Data Index: 1359393 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0841. Min Act: -0.0001

Data Index: 916773 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0871. Min Act: -0.0000

Data Index: 1047513 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0863. Min Act: -0.0001

Data Index: 1121902 (C4 (Web Text))

Max Activating Token Index: 999

Text #18

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0858. Min Act: -0.0001

Data Index: 1074853 (C4 (Web Text))

Max Activating Token Index: 659

Text #19

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0849. Min Act: -0.0001

Data Index: 100504 (C4 (Web Text))

Max Activating Token Index: 206