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

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

Neuron 3737 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: 6.6453. Min Range: -6.6453

Max Act: 6.6453. Min Act: -0.0000

Data Index: 879531 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 6.6453. Min Range: -6.6453

Max Act: 6.5360. Min Act: -0.0000

Data Index: 757167 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 6.6453. Min Range: -6.6453

Max Act: 6.4581. Min Act: -0.0000

Data Index: 367731 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 6.6453. Min Range: -6.6453

Max Act: 6.4277. Min Act: -0.0000

Data Index: 937102 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 6.6453. Min Range: -6.6453

Max Act: 6.2645. Min Act: -0.0000

Data Index: 1052897 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 6.6453. Min Range: -6.6453

Max Act: 6.2068. Min Act: -0.0000

Data Index: 153002 (C4 (Web Text))

Max Activating Token Index: 730

Text #6

Max Range: 6.6453. Min Range: -6.6453

Max Act: 6.2262. Min Act: -0.0000

Data Index: 1333531 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 6.6453. Min Range: -6.6453

Max Act: 5.9953. Min Act: -0.0000

Data Index: 1016554 (C4 (Web Text))

Max Activating Token Index: 906

Text #8

Max Range: 6.6453. Min Range: -6.6453

Max Act: 5.4817. Min Act: -0.0000

Data Index: 1013804 (C4 (Web Text))

Max Activating Token Index: 81

Text #9

Max Range: 6.6453. Min Range: -6.6453

Max Act: 5.6360. Min Act: -0.0000

Data Index: 525972 (C4 (Web Text))

Max Activating Token Index: 517

Text #10

Max Range: 6.6453. Min Range: -6.6453

Max Act: 6.0190. Min Act: -0.0000

Data Index: 243570 (C4 (Web Text))

Max Activating Token Index: 425

Text #11

Max Range: 6.6453. Min Range: -6.6453

Max Act: 5.7890. Min Act: -0.0000

Data Index: 340299 (C4 (Web Text))

Max Activating Token Index: 57

Text #12

Max Range: 6.6453. Min Range: -6.6453

Max Act: 5.7486. Min Act: -0.0000

Data Index: 410494 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 6.6453. Min Range: -6.6453

Max Act: 5.7096. Min Act: -0.0000

Data Index: 892171 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 6.6453. Min Range: -6.6453

Max Act: 5.4220. Min Act: -0.0000

Data Index: 856226 (C4 (Web Text))

Max Activating Token Index: 996

Text #15

Max Range: 6.6453. Min Range: -6.6453

Max Act: 5.6702. Min Act: -0.0000

Data Index: 429843 (C4 (Web Text))

Max Activating Token Index: 206

Text #16

Max Range: 6.6453. Min Range: -6.6453

Max Act: 5.6596. Min Act: -0.0000

Data Index: 501444 (C4 (Web Text))

Max Activating Token Index: 689

Text #17

Max Range: 6.6453. Min Range: -6.6453

Max Act: 5.7941. Min Act: -0.0000

Data Index: 772794 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 6.6453. Min Range: -6.6453

Max Act: 5.5933. Min Act: -0.0000

Data Index: 1198176 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 6.6453. Min Range: -6.6453

Max Act: 5.5745. Min Act: -0.0000

Data Index: 1123516 (C4 (Web Text))

Max Activating Token Index: 25