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

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

Neuron 6138 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.2723. Min Act: -0.0000

Data Index: 1102494 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.2329. Min Act: -0.0000

Data Index: 16228 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.2303. Min Act: -0.0000

Data Index: 975226 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.2143. Min Act: -0.0000

Data Index: 789514 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.2184. Min Act: -0.0000

Data Index: 1010323 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.2145. Min Act: -0.0000

Data Index: 724298 (C4 (Web Text))

Max Activating Token Index: 114

Text #6

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.2101. Min Act: -0.0000

Data Index: 188244 (C4 (Web Text))

Max Activating Token Index: 46

Text #7

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.2109. Min Act: -0.0000

Data Index: 37248 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.2143. Min Act: -0.0000

Data Index: 927756 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.1993. Min Act: -0.0000

Data Index: 324090 (C4 (Web Text))

Max Activating Token Index: 93

Text #10

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.2045. Min Act: -0.0000

Data Index: 742628 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.2117. Min Act: -0.0000

Data Index: 714089 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.2112. Min Act: -0.0000

Data Index: 136028 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.2011. Min Act: -0.0000

Data Index: 801315 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.1920. Min Act: -0.0000

Data Index: 750126 (C4 (Web Text))

Max Activating Token Index: 19

Text #15

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.1978. Min Act: -0.0000

Data Index: 1037707 (C4 (Web Text))

Max Activating Token Index: 13

Text #16

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.2058. Min Act: -0.0000

Data Index: 196084 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.1900. Min Act: -0.0000

Data Index: 175886 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.1946. Min Act: -0.0000

Data Index: 557814 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.1936. Min Act: -0.0000

Data Index: 875665 (C4 (Web Text))

Max Activating Token Index: 50