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

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

Neuron 4609 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7187. Min Range: -0.7187

Max Act: 0.7187. Min Act: -0.0000

Data Index: 837423 (C4 (Web Text))

Max Activating Token Index: 1011

Text #1

Max Range: 0.7187. Min Range: -0.7187

Max Act: 0.5822. Min Act: -0.0000

Data Index: 1224586 (C4 (Web Text))

Max Activating Token Index: 371

Text #2

Max Range: 0.7187. Min Range: -0.7187

Max Act: 0.5886. Min Act: -0.0000

Data Index: 1166904 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 0.7187. Min Range: -0.7187

Max Act: 0.5665. Min Act: -0.0000

Data Index: 88257 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 0.7187. Min Range: -0.7187

Max Act: 0.5497. Min Act: -0.0000

Data Index: 133088 (C4 (Web Text))

Max Activating Token Index: 410

Text #5

Max Range: 0.7187. Min Range: -0.7187

Max Act: 0.5652. Min Act: -0.0000

Data Index: 1061199 (C4 (Web Text))

Max Activating Token Index: 214

Text #6

Max Range: 0.7187. Min Range: -0.7187

Max Act: 0.5799. Min Act: -0.0000

Data Index: 655113 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 0.7187. Min Range: -0.7187

Max Act: 0.5439. Min Act: -0.0000

Data Index: 1309826 (C4 (Web Text))

Max Activating Token Index: 982

Text #8

Max Range: 0.7187. Min Range: -0.7187

Max Act: 0.5551. Min Act: -0.0000

Data Index: 1118499 (C4 (Web Text))

Max Activating Token Index: 578

Text #9

Max Range: 0.7187. Min Range: -0.7187

Max Act: 0.5337. Min Act: -0.0000

Data Index: 613163 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 0.7187. Min Range: -0.7187

Max Act: 0.4983. Min Act: -0.0000

Data Index: 581967 (C4 (Web Text))

Max Activating Token Index: 284

Text #11

Max Range: 0.7187. Min Range: -0.7187

Max Act: 0.5006. Min Act: -0.0000

Data Index: 695666 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 0.7187. Min Range: -0.7187

Max Act: 0.4989. Min Act: -0.0000

Data Index: 100448 (C4 (Web Text))

Max Activating Token Index: 711

Text #13

Max Range: 0.7187. Min Range: -0.7187

Max Act: 0.5149. Min Act: -0.0000

Data Index: 554349 (C4 (Web Text))

Max Activating Token Index: 592

Text #14

Max Range: 0.7187. Min Range: -0.7187

Max Act: 0.4982. Min Act: -0.0000

Data Index: 454923 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 0.7187. Min Range: -0.7187

Max Act: 0.4794. Min Act: -0.0000

Data Index: 50028 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 0.7187. Min Range: -0.7187

Max Act: 0.4970. Min Act: -0.0000

Data Index: 346535 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 0.7187. Min Range: -0.7187

Max Act: 0.4853. Min Act: -0.0000

Data Index: 1288678 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 0.7187. Min Range: -0.7187

Max Act: 0.4550. Min Act: -0.0000

Data Index: 1343547 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 0.7187. Min Range: -0.7187

Max Act: 0.4840. Min Act: -0.0000

Data Index: 1059367 (C4 (Web Text))

Max Activating Token Index: 1002