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

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

Neuron 3065 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: 0.1297. Min Range: -0.1297

Max Act: 0.1297. Min Act: -0.0000

Data Index: 1277947 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1063. Min Act: -0.0001

Data Index: 544036 (C4 (Web Text))

Max Activating Token Index: 342

Text #2

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1095. Min Act: -0.0001

Data Index: 1011705 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1053. Min Act: -0.0000

Data Index: 1217790 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1007. Min Act: -0.0000

Data Index: 1267774 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0999. Min Act: -0.0000

Data Index: 658716 (C4 (Web Text))

Max Activating Token Index: 871

Text #6

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1057. Min Act: -0.0001

Data Index: 36712 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1005. Min Act: -0.0000

Data Index: 741772 (C4 (Web Text))

Max Activating Token Index: 339

Text #8

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0946. Min Act: -0.0001

Data Index: 403861 (C4 (Web Text))

Max Activating Token Index: 587

Text #9

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0941. Min Act: -0.0000

Data Index: 230126 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0915. Min Act: -0.0000

Data Index: 367800 (C4 (Web Text))

Max Activating Token Index: 949

Text #11

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0974. Min Act: -0.0000

Data Index: 247332 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0908. Min Act: -0.0001

Data Index: 195188 (C4 (Web Text))

Max Activating Token Index: 1010

Text #13

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0936. Min Act: -0.0000

Data Index: 52857 (C4 (Web Text))

Max Activating Token Index: 960

Text #14

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0910. Min Act: -0.0000

Data Index: 849025 (C4 (Web Text))

Max Activating Token Index: 348

Text #15

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0930. Min Act: -0.0000

Data Index: 189631 (C4 (Web Text))

Max Activating Token Index: 742

Text #16

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0972. Min Act: -0.0000

Data Index: 847065 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0964. Min Act: -0.0001

Data Index: 256761 (C4 (Web Text))

Max Activating Token Index: 566

Text #18

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0941. Min Act: -0.0001

Data Index: 181800 (C4 (Web Text))

Max Activating Token Index: 927

Text #19

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0921. Min Act: -0.0000

Data Index: 36811 (C4 (Web Text))

Max Activating Token Index: 902