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

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

Neuron 4085 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: 0.0977. Min Range: -0.0977

Max Act: 0.0967. Min Act: -0.0001

Data Index: 989820 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0916. Min Act: -0.0001

Data Index: 456513 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0977. Min Act: -0.0002

Data Index: 389228 (C4 (Web Text))

Max Activating Token Index: 767

Text #3

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0921. Min Act: -0.0002

Data Index: 1081550 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0862. Min Act: -0.0002

Data Index: 828582 (C4 (Web Text))

Max Activating Token Index: 815

Text #5

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0872. Min Act: -0.0002

Data Index: 356863 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0844. Min Act: -0.0001

Data Index: 839805 (C4 (Web Text))

Max Activating Token Index: 770

Text #7

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0960. Min Act: -0.0002

Data Index: 48882 (C4 (Web Text))

Max Activating Token Index: 187

Text #8

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0844. Min Act: -0.0001

Data Index: 196094 (C4 (Web Text))

Max Activating Token Index: 927

Text #9

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0804. Min Act: -0.0002

Data Index: 702149 (C4 (Web Text))

Max Activating Token Index: 491

Text #10

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0745. Min Act: -0.0002

Data Index: 1275882 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0785. Min Act: -0.0001

Data Index: 657699 (C4 (Web Text))

Max Activating Token Index: 173

Text #12

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0839. Min Act: -0.0002

Data Index: 437897 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0869. Min Act: -0.0001

Data Index: 236274 (C4 (Web Text))

Max Activating Token Index: 656

Text #14

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0771. Min Act: -0.0001

Data Index: 1296789 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0719. Min Act: -0.0002

Data Index: 1075577 (C4 (Web Text))

Max Activating Token Index: 279

Text #16

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0799. Min Act: -0.0002

Data Index: 660109 (C4 (Web Text))

Max Activating Token Index: 1015

Text #17

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0811. Min Act: -0.0002

Data Index: 810519 (C4 (Web Text))

Max Activating Token Index: 654

Text #18

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0816. Min Act: -0.0001

Data Index: 1330704 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0759. Min Act: -0.0002

Data Index: 600589 (C4 (Web Text))

Max Activating Token Index: 904