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

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

Neuron 3362 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: 0.0005. Min Range: -0.0005

Max Act: 0.0005. Min Act: -0.0003

Data Index: 963640 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 0.0005. Min Range: -0.0005

Max Act: 0.0005. Min Act: -0.0003

Data Index: 870521 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0005. Min Range: -0.0005

Max Act: 0.0004. Min Act: -0.0003

Data Index: 1153323 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 0.0005. Min Range: -0.0005

Max Act: 0.0004. Min Act: -0.0003

Data Index: 30089 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 0.0005. Min Range: -0.0005

Max Act: 0.0005. Min Act: -0.0003

Data Index: 215276 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0005. Min Range: -0.0005

Max Act: 0.0004. Min Act: -0.0003

Data Index: 169308 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0005. Min Range: -0.0005

Max Act: 0.0004. Min Act: -0.0003

Data Index: 816170 (C4 (Web Text))

Max Activating Token Index: 989

Text #7

Max Range: 0.0005. Min Range: -0.0005

Max Act: 0.0004. Min Act: -0.0003

Data Index: 84827 (C4 (Web Text))

Max Activating Token Index: 999

Text #8

Max Range: 0.0005. Min Range: -0.0005

Max Act: 0.0003. Min Act: -0.0003

Data Index: 1039165 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0005. Min Range: -0.0005

Max Act: 0.0004. Min Act: -0.0003

Data Index: 509305 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 0.0005. Min Range: -0.0005

Max Act: 0.0003. Min Act: -0.0003

Data Index: 807066 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0005. Min Range: -0.0005

Max Act: 0.0003. Min Act: -0.0003

Data Index: 1131544 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0005. Min Range: -0.0005

Max Act: 0.0003. Min Act: -0.0003

Data Index: 373634 (C4 (Web Text))

Max Activating Token Index: 975

Text #13

Max Range: 0.0005. Min Range: -0.0005

Max Act: 0.0003. Min Act: -0.0003

Data Index: 949332 (C4 (Web Text))

Max Activating Token Index: 1009

Text #14

Max Range: 0.0005. Min Range: -0.0005

Max Act: 0.0003. Min Act: -0.0003

Data Index: 322953 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 0.0005. Min Range: -0.0005

Max Act: 0.0003. Min Act: -0.0003

Data Index: 341799 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 0.0005. Min Range: -0.0005

Max Act: 0.0003. Min Act: -0.0003

Data Index: 56212 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 0.0005. Min Range: -0.0005

Max Act: 0.0002. Min Act: -0.0003

Data Index: 524822 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0005. Min Range: -0.0005

Max Act: 0.0003. Min Act: -0.0003

Data Index: 393689 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0005. Min Range: -0.0005

Max Act: 0.0003. Min Act: -0.0003

Data Index: 215452 (C4 (Web Text))

Max Activating Token Index: 1023