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

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

Neuron 505 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0009. Min Range: -0.0009

Max Act: 0.0009. Min Act: -0.0003

Data Index: 674435 (C4 (Web Text))

Max Activating Token Index: 879

Text #1

Max Range: 0.0009. Min Range: -0.0009

Max Act: 0.0009. Min Act: -0.0003

Data Index: 384940 (C4 (Web Text))

Max Activating Token Index: 985

Text #2

Max Range: 0.0009. Min Range: -0.0009

Max Act: 0.0008. Min Act: -0.0003

Data Index: 1143597 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 0.0009. Min Range: -0.0009

Max Act: 0.0008. Min Act: -0.0003

Data Index: 855182 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0009. Min Range: -0.0009

Max Act: 0.0008. Min Act: -0.0003

Data Index: 92921 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 0.0009. Min Range: -0.0009

Max Act: 0.0007. Min Act: -0.0003

Data Index: 473366 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 0.0009. Min Range: -0.0009

Max Act: 0.0007. Min Act: -0.0003

Data Index: 204767 (C4 (Web Text))

Max Activating Token Index: 1003

Text #7

Max Range: 0.0009. Min Range: -0.0009

Max Act: 0.0008. Min Act: -0.0003

Data Index: 770258 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 0.0009. Min Range: -0.0009

Max Act: 0.0007. Min Act: -0.0003

Data Index: 93134 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0009. Min Range: -0.0009

Max Act: 0.0005. Min Act: -0.0003

Data Index: 360761 (C4 (Web Text))

Max Activating Token Index: 956

Text #10

Max Range: 0.0009. Min Range: -0.0009

Max Act: 0.0007. Min Act: -0.0003

Data Index: 929146 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 0.0009. Min Range: -0.0009

Max Act: 0.0006. Min Act: -0.0003

Data Index: 89635 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 0.0009. Min Range: -0.0009

Max Act: 0.0006. Min Act: -0.0003

Data Index: 254092 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0009. Min Range: -0.0009

Max Act: 0.0006. Min Act: -0.0003

Data Index: 448302 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0009. Min Range: -0.0009

Max Act: 0.0006. Min Act: -0.0003

Data Index: 805906 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0009. Min Range: -0.0009

Max Act: 0.0006. Min Act: -0.0003

Data Index: 205238 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 0.0009. Min Range: -0.0009

Max Act: 0.0005. Min Act: -0.0003

Data Index: 522297 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0009. Min Range: -0.0009

Max Act: 0.0006. Min Act: -0.0003

Data Index: 311372 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 0.0009. Min Range: -0.0009

Max Act: 0.0005. Min Act: -0.0003

Data Index: 1254866 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0009. Min Range: -0.0009

Max Act: 0.0005. Min Act: -0.0003

Data Index: 466071 (C4 (Web Text))

Max Activating Token Index: 1020