Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2535 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2998. Min Range: -0.2998

Max Act: 0.2998. Min Act: -0.0001

Data Index: 917530 (C4 (Web Text))

Max Activating Token Index: 284

Text #1

Max Range: 0.2998. Min Range: -0.2998

Max Act: 0.2866. Min Act: -0.0001

Data Index: 1351093 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 0.2998. Min Range: -0.2998

Max Act: 0.2122. Min Act: -0.0001

Data Index: 939480 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 0.2998. Min Range: -0.2998

Max Act: 0.2300. Min Act: -0.0001

Data Index: 1132456 (C4 (Web Text))

Max Activating Token Index: 22

Text #4

Max Range: 0.2998. Min Range: -0.2998

Max Act: 0.2360. Min Act: -0.0001

Data Index: 606285 (C4 (Web Text))

Max Activating Token Index: 538

Text #5

Max Range: 0.2998. Min Range: -0.2998

Max Act: 0.2281. Min Act: -0.0001

Data Index: 1189251 (C4 (Web Text))

Max Activating Token Index: 848

Text #6

Max Range: 0.2998. Min Range: -0.2998

Max Act: 0.2114. Min Act: -0.0001

Data Index: 1119420 (C4 (Web Text))

Max Activating Token Index: 7

Text #7

Max Range: 0.2998. Min Range: -0.2998

Max Act: 0.1991. Min Act: -0.0001

Data Index: 1205238 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 0.2998. Min Range: -0.2998

Max Act: 0.2070. Min Act: -0.0001

Data Index: 342603 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 0.2998. Min Range: -0.2998

Max Act: 0.1986. Min Act: -0.0001

Data Index: 279538 (C4 (Web Text))

Max Activating Token Index: 944

Text #10

Max Range: 0.2998. Min Range: -0.2998

Max Act: 0.1992. Min Act: -0.0001

Data Index: 956773 (C4 (Web Text))

Max Activating Token Index: 205

Text #11

Max Range: 0.2998. Min Range: -0.2998

Max Act: 0.1963. Min Act: -0.0001

Data Index: 1028792 (C4 (Web Text))

Max Activating Token Index: 890

Text #12

Max Range: 0.2998. Min Range: -0.2998

Max Act: 0.1998. Min Act: -0.0001

Data Index: 199332 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 0.2998. Min Range: -0.2998

Max Act: 0.2105. Min Act: -0.0001

Data Index: 244367 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 0.2998. Min Range: -0.2998

Max Act: 0.2014. Min Act: -0.0001

Data Index: 548819 (C4 (Web Text))

Max Activating Token Index: 520

Text #15

Max Range: 0.2998. Min Range: -0.2998

Max Act: 0.1981. Min Act: -0.0001

Data Index: 274538 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 0.2998. Min Range: -0.2998

Max Act: 0.1900. Min Act: -0.0001

Data Index: 707274 (C4 (Web Text))

Max Activating Token Index: 715

Text #17

Max Range: 0.2998. Min Range: -0.2998

Max Act: 0.2076. Min Act: -0.0001

Data Index: 742616 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 0.2998. Min Range: -0.2998

Max Act: 0.1886. Min Act: -0.0001

Data Index: 7113 (C4 (Web Text))

Max Activating Token Index: 215

Text #19

Max Range: 0.2998. Min Range: -0.2998

Max Act: 0.1852. Min Act: -0.0001

Data Index: 1172945 (C4 (Web Text))

Max Activating Token Index: 349