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

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

Neuron 2797 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1762. Min Act: -0.0001

Data Index: 196545 (C4 (Web Text))

Max Activating Token Index: 573

Text #1

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1684. Min Act: -0.0001

Data Index: 703574 (C4 (Web Text))

Max Activating Token Index: 452

Text #2

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1582. Min Act: -0.0001

Data Index: 213369 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1547. Min Act: -0.0001

Data Index: 833072 (C4 (Web Text))

Max Activating Token Index: 582

Text #4

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1430. Min Act: -0.0001

Data Index: 37521 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1320. Min Act: -0.0001

Data Index: 422992 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1211. Min Act: -0.0001

Data Index: 646922 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1189. Min Act: -0.0001

Data Index: 1037899 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1200. Min Act: -0.0001

Data Index: 672844 (C4 (Web Text))

Max Activating Token Index: 980

Text #9

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.0928. Min Act: -0.0001

Data Index: 400462 (C4 (Web Text))

Max Activating Token Index: 189

Text #10

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.0983. Min Act: -0.0001

Data Index: 414880 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1080. Min Act: -0.0001

Data Index: 126266 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1045. Min Act: -0.0001

Data Index: 245912 (C4 (Web Text))

Max Activating Token Index: 131

Text #13

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1005. Min Act: -0.0001

Data Index: 298890 (C4 (Web Text))

Max Activating Token Index: 613

Text #14

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.0903. Min Act: -0.0001

Data Index: 802750 (C4 (Web Text))

Max Activating Token Index: 372

Text #15

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.0988. Min Act: -0.0001

Data Index: 1049700 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.0945. Min Act: -0.0001

Data Index: 816723 (C4 (Web Text))

Max Activating Token Index: 271

Text #17

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.0878. Min Act: -0.0001

Data Index: 736499 (C4 (Web Text))

Max Activating Token Index: 435

Text #18

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.0975. Min Act: -0.0001

Data Index: 187051 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.0962. Min Act: -0.0001

Data Index: 159694 (C4 (Web Text))

Max Activating Token Index: 361