Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4574 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2752. Min Act: -0.0001

Data Index: 539887 (C4 (Web Text))

Max Activating Token Index: 165

Text #1

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2468. Min Act: -0.0001

Data Index: 607029 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2198. Min Act: -0.0001

Data Index: 177836 (C4 (Web Text))

Max Activating Token Index: 486

Text #3

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2378. Min Act: -0.0001

Data Index: 544915 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2119. Min Act: -0.0001

Data Index: 50382 (C4 (Web Text))

Max Activating Token Index: 586

Text #5

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1964. Min Act: -0.0001

Data Index: 1270416 (C4 (Web Text))

Max Activating Token Index: 372

Text #6

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1961. Min Act: -0.0001

Data Index: 322261 (C4 (Web Text))

Max Activating Token Index: 561

Text #7

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2024. Min Act: -0.0001

Data Index: 961848 (C4 (Web Text))

Max Activating Token Index: 694

Text #8

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1956. Min Act: -0.0001

Data Index: 899446 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1866. Min Act: -0.0001

Data Index: 1104749 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1997. Min Act: -0.0001

Data Index: 728398 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1871. Min Act: -0.0001

Data Index: 1001868 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1998. Min Act: -0.0001

Data Index: 228001 (C4 (Web Text))

Max Activating Token Index: 235

Text #13

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1868. Min Act: -0.0001

Data Index: 600359 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1994. Min Act: -0.0001

Data Index: 314983 (C4 (Web Text))

Max Activating Token Index: 501

Text #15

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1970. Min Act: -0.0001

Data Index: 644326 (C4 (Web Text))

Max Activating Token Index: 975

Text #16

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2052. Min Act: -0.0001

Data Index: 750353 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1888. Min Act: -0.0001

Data Index: 1250028 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1958. Min Act: -0.0001

Data Index: 122031 (C4 (Web Text))

Max Activating Token Index: 257

Text #19

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2003. Min Act: -0.0001

Data Index: 986252 (C4 (Web Text))

Max Activating Token Index: 195