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

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

Neuron 3840 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: 0.0793. Min Range: -0.0793

Max Act: 0.0793. Min Act: -0.0001

Data Index: 127204 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0784. Min Act: -0.0002

Data Index: 594462 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0633. Min Act: -0.0002

Data Index: 67098 (C4 (Web Text))

Max Activating Token Index: 859

Text #3

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0634. Min Act: -0.0001

Data Index: 131856 (C4 (Web Text))

Max Activating Token Index: 714

Text #4

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0634. Min Act: -0.0001

Data Index: 1569305 (Python Code)

Max Activating Token Index: 457

Text #5

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0656. Min Act: -0.0001

Data Index: 1586170 (Python Code)

Max Activating Token Index: 1018

Text #6

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0678. Min Act: -0.0001

Data Index: 1316718 (C4 (Web Text))

Max Activating Token Index: 3

Text #7

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0697. Min Act: -0.0001

Data Index: 832859 (C4 (Web Text))

Max Activating Token Index: 473

Text #8

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0675. Min Act: -0.0002

Data Index: 868805 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0665. Min Act: -0.0002

Data Index: 513392 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0567. Min Act: -0.0001

Data Index: 1363530 (Python Code)

Max Activating Token Index: 696

Text #11

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0641. Min Act: -0.0001

Data Index: 852392 (C4 (Web Text))

Max Activating Token Index: 49

Text #12

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0663. Min Act: -0.0002

Data Index: 30198 (C4 (Web Text))

Max Activating Token Index: 25

Text #13

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0733. Min Act: -0.0002

Data Index: 1126735 (C4 (Web Text))

Max Activating Token Index: 267

Text #14

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0685. Min Act: -0.0002

Data Index: 250764 (C4 (Web Text))

Max Activating Token Index: 380

Text #15

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0683. Min Act: -0.0002

Data Index: 1251701 (C4 (Web Text))

Max Activating Token Index: 142

Text #16

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0626. Min Act: -0.0001

Data Index: 1643377 (Python Code)

Max Activating Token Index: 976

Text #17

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0630. Min Act: -0.0001

Data Index: 672954 (C4 (Web Text))

Max Activating Token Index: 281

Text #18

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0649. Min Act: -0.0002

Data Index: 106565 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0644. Min Act: -0.0001

Data Index: 2885 (C4 (Web Text))

Max Activating Token Index: 704