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

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

Neuron 3681 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0228. Min Range: -1.0228

Max Act: 1.0228. Min Act: -0.0001

Data Index: 317951 (C4 (Web Text))

Max Activating Token Index: 653

Text #1

Max Range: 1.0228. Min Range: -1.0228

Max Act: 0.7787. Min Act: -0.0001

Data Index: 1149965 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 1.0228. Min Range: -1.0228

Max Act: 0.6917. Min Act: -0.0002

Data Index: 293068 (C4 (Web Text))

Max Activating Token Index: 732

Text #3

Max Range: 1.0228. Min Range: -1.0228

Max Act: 0.6969. Min Act: -0.0001

Data Index: 38964 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 1.0228. Min Range: -1.0228

Max Act: 0.7020. Min Act: -0.0001

Data Index: 1343251 (C4 (Web Text))

Max Activating Token Index: 87

Text #5

Max Range: 1.0228. Min Range: -1.0228

Max Act: 0.6622. Min Act: -0.0001

Data Index: 80620 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 1.0228. Min Range: -1.0228

Max Act: 0.7262. Min Act: -0.0001

Data Index: 222317 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 1.0228. Min Range: -1.0228

Max Act: 0.6860. Min Act: -0.0002

Data Index: 327244 (C4 (Web Text))

Max Activating Token Index: 971

Text #8

Max Range: 1.0228. Min Range: -1.0228

Max Act: 0.6356. Min Act: -0.0001

Data Index: 825269 (C4 (Web Text))

Max Activating Token Index: 359

Text #9

Max Range: 1.0228. Min Range: -1.0228

Max Act: 0.6561. Min Act: -0.0001

Data Index: 858782 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 1.0228. Min Range: -1.0228

Max Act: 0.6782. Min Act: -0.0001

Data Index: 1067743 (C4 (Web Text))

Max Activating Token Index: 575

Text #11

Max Range: 1.0228. Min Range: -1.0228

Max Act: 0.6676. Min Act: -0.0001

Data Index: 1340546 (C4 (Web Text))

Max Activating Token Index: 998

Text #12

Max Range: 1.0228. Min Range: -1.0228

Max Act: 0.6435. Min Act: -0.0001

Data Index: 810309 (C4 (Web Text))

Max Activating Token Index: 845

Text #13

Max Range: 1.0228. Min Range: -1.0228

Max Act: 0.5977. Min Act: -0.0001

Data Index: 85736 (C4 (Web Text))

Max Activating Token Index: 653

Text #14

Max Range: 1.0228. Min Range: -1.0228

Max Act: 0.6350. Min Act: -0.0001

Data Index: 623627 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 1.0228. Min Range: -1.0228

Max Act: 0.5941. Min Act: -0.0001

Data Index: 729527 (C4 (Web Text))

Max Activating Token Index: 11

Text #16

Max Range: 1.0228. Min Range: -1.0228

Max Act: 0.6129. Min Act: -0.0001

Data Index: 891493 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 1.0228. Min Range: -1.0228

Max Act: 0.6074. Min Act: -0.0002

Data Index: 110998 (C4 (Web Text))

Max Activating Token Index: 135

Text #18

Max Range: 1.0228. Min Range: -1.0228

Max Act: 0.5807. Min Act: -0.0001

Data Index: 711385 (C4 (Web Text))

Max Activating Token Index: 317

Text #19

Max Range: 1.0228. Min Range: -1.0228

Max Act: 0.6133. Min Act: -0.0001

Data Index: 764126 (C4 (Web Text))

Max Activating Token Index: 229