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

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

Neuron 1791 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: 0.0681. Min Range: -0.0681

Max Act: 0.0681. Min Act: -0.0002

Data Index: 695947 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0616. Min Act: -0.0002

Data Index: 837363 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0623. Min Act: -0.0001

Data Index: 1058570 (C4 (Web Text))

Max Activating Token Index: 417

Text #3

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0566. Min Act: -0.0001

Data Index: 989415 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0563. Min Act: -0.0002

Data Index: 1014279 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0581. Min Act: -0.0002

Data Index: 405826 (C4 (Web Text))

Max Activating Token Index: 210

Text #6

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0560. Min Act: -0.0002

Data Index: 608884 (C4 (Web Text))

Max Activating Token Index: 918

Text #7

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0532. Min Act: -0.0002

Data Index: 364638 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0566. Min Act: -0.0001

Data Index: 921394 (C4 (Web Text))

Max Activating Token Index: 500

Text #9

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0544. Min Act: -0.0001

Data Index: 1076907 (C4 (Web Text))

Max Activating Token Index: 53

Text #10

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0566. Min Act: -0.0001

Data Index: 1248908 (C4 (Web Text))

Max Activating Token Index: 409

Text #11

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0560. Min Act: -0.0002

Data Index: 327236 (C4 (Web Text))

Max Activating Token Index: 893

Text #12

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0577. Min Act: -0.0002

Data Index: 457490 (C4 (Web Text))

Max Activating Token Index: 510

Text #13

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0536. Min Act: -0.0002

Data Index: 1084179 (C4 (Web Text))

Max Activating Token Index: 170

Text #14

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0549. Min Act: -0.0002

Data Index: 815477 (C4 (Web Text))

Max Activating Token Index: 36

Text #15

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1285733 (C4 (Web Text))

Max Activating Token Index: 196

Text #16

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0523. Min Act: -0.0002

Data Index: 1281890 (C4 (Web Text))

Max Activating Token Index: 338

Text #17

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0540. Min Act: -0.0002

Data Index: 633201 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0537. Min Act: -0.0001

Data Index: 826380 (C4 (Web Text))

Max Activating Token Index: 4

Text #19

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0555. Min Act: -0.0002

Data Index: 893018 (C4 (Web Text))

Max Activating Token Index: 376