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

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

Neuron 5168 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6069. Min Range: -3.6069

Max Act: 3.6069. Min Act: -0.0000

Data Index: 1020219 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 3.6069. Min Range: -3.6069

Max Act: 3.2633. Min Act: -0.0000

Data Index: 1617728 (Python Code)

Max Activating Token Index: 9

Text #2

Max Range: 3.6069. Min Range: -3.6069

Max Act: 3.2481. Min Act: -0.0000

Data Index: 869776 (C4 (Web Text))

Max Activating Token Index: 936

Text #3

Max Range: 3.6069. Min Range: -3.6069

Max Act: 3.1597. Min Act: -0.0000

Data Index: 1095695 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 3.6069. Min Range: -3.6069

Max Act: 3.0898. Min Act: -0.0000

Data Index: 1326656 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 3.6069. Min Range: -3.6069

Max Act: 2.8935. Min Act: -0.0000

Data Index: 180486 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 3.6069. Min Range: -3.6069

Max Act: 2.8676. Min Act: -0.0000

Data Index: 1291879 (C4 (Web Text))

Max Activating Token Index: 733

Text #7

Max Range: 3.6069. Min Range: -3.6069

Max Act: 2.7277. Min Act: -0.0000

Data Index: 558857 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 3.6069. Min Range: -3.6069

Max Act: 2.6111. Min Act: -0.0000

Data Index: 449735 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 3.6069. Min Range: -3.6069

Max Act: 2.5971. Min Act: -0.0000

Data Index: 467919 (C4 (Web Text))

Max Activating Token Index: 964

Text #10

Max Range: 3.6069. Min Range: -3.6069

Max Act: 2.5589. Min Act: -0.0000

Data Index: 818876 (C4 (Web Text))

Max Activating Token Index: 1022

Text #11

Max Range: 3.6069. Min Range: -3.6069

Max Act: 2.8262. Min Act: -0.0000

Data Index: 1600845 (Python Code)

Max Activating Token Index: 20

Text #12

Max Range: 3.6069. Min Range: -3.6069

Max Act: 2.8013. Min Act: -0.0000

Data Index: 818333 (C4 (Web Text))

Max Activating Token Index: 559

Text #13

Max Range: 3.6069. Min Range: -3.6069

Max Act: 2.7934. Min Act: -0.0000

Data Index: 571659 (C4 (Web Text))

Max Activating Token Index: 415

Text #14

Max Range: 3.6069. Min Range: -3.6069

Max Act: 2.6232. Min Act: -0.0000

Data Index: 829199 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 3.6069. Min Range: -3.6069

Max Act: 2.6244. Min Act: -0.0000

Data Index: 798693 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 3.6069. Min Range: -3.6069

Max Act: 2.5780. Min Act: -0.0000

Data Index: 373880 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 3.6069. Min Range: -3.6069

Max Act: 2.7018. Min Act: -0.0000

Data Index: 261440 (C4 (Web Text))

Max Activating Token Index: 118

Text #18

Max Range: 3.6069. Min Range: -3.6069

Max Act: 2.5524. Min Act: -0.0000

Data Index: 208992 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 3.6069. Min Range: -3.6069

Max Act: 2.6736. Min Act: -0.0000

Data Index: 1074690 (C4 (Web Text))

Max Activating Token Index: 474