Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 541 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0977. Min Act: -0.0002

Data Index: 975785 (C4 (Web Text))

Max Activating Token Index: 463

Text #1

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0856. Min Act: -0.0002

Data Index: 1313321 (C4 (Web Text))

Max Activating Token Index: 1022

Text #2

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0842. Min Act: -0.0002

Data Index: 1551791 (Python Code)

Max Activating Token Index: 803

Text #3

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0804. Min Act: -0.0001

Data Index: 618811 (C4 (Web Text))

Max Activating Token Index: 403

Text #4

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0859. Min Act: -0.0001

Data Index: 943949 (C4 (Web Text))

Max Activating Token Index: 943

Text #5

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0757. Min Act: -0.0002

Data Index: 531945 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0819. Min Act: -0.0002

Data Index: 487563 (C4 (Web Text))

Max Activating Token Index: 965

Text #7

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0781. Min Act: -0.0002

Data Index: 1189788 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0781. Min Act: -0.0002

Data Index: 79502 (C4 (Web Text))

Max Activating Token Index: 968

Text #9

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0775. Min Act: -0.0002

Data Index: 661351 (C4 (Web Text))

Max Activating Token Index: 978

Text #10

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0762. Min Act: -0.0002

Data Index: 1050552 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0732. Min Act: -0.0002

Data Index: 786203 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0741. Min Act: -0.0002

Data Index: 1152559 (C4 (Web Text))

Max Activating Token Index: 223

Text #13

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0753. Min Act: -0.0002

Data Index: 669661 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0755. Min Act: -0.0002

Data Index: 788986 (C4 (Web Text))

Max Activating Token Index: 765

Text #15

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0729. Min Act: -0.0002

Data Index: 1054810 (C4 (Web Text))

Max Activating Token Index: 963

Text #16

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0673. Min Act: -0.0002

Data Index: 99562 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0695. Min Act: -0.0002

Data Index: 370276 (C4 (Web Text))

Max Activating Token Index: 568

Text #18

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0715. Min Act: -0.0002

Data Index: 608797 (C4 (Web Text))

Max Activating Token Index: 416

Text #19

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0717. Min Act: -0.0002

Data Index: 42438 (C4 (Web Text))

Max Activating Token Index: 846