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

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

Neuron 2978 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.1071. Min Act: -0.0000

Data Index: 372444 (C4 (Web Text))

Max Activating Token Index: 776

Text #1

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.1097. Min Act: -0.0000

Data Index: 1065818 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0935. Min Act: -0.0000

Data Index: 107636 (C4 (Web Text))

Max Activating Token Index: 965

Text #3

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0950. Min Act: -0.0000

Data Index: 1145744 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0992. Min Act: -0.0000

Data Index: 811294 (C4 (Web Text))

Max Activating Token Index: 577

Text #5

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0801. Min Act: -0.0000

Data Index: 513672 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0868. Min Act: -0.0000

Data Index: 333566 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0797. Min Act: -0.0000

Data Index: 347711 (C4 (Web Text))

Max Activating Token Index: 953

Text #8

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0843. Min Act: -0.0000

Data Index: 97208 (C4 (Web Text))

Max Activating Token Index: 355

Text #9

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0875. Min Act: -0.0000

Data Index: 1073447 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0865. Min Act: -0.0000

Data Index: 1036684 (C4 (Web Text))

Max Activating Token Index: 262

Text #11

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0818. Min Act: -0.0000

Data Index: 1641161 (Python Code)

Max Activating Token Index: 199

Text #12

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0773. Min Act: -0.0000

Data Index: 429096 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0764. Min Act: -0.0000

Data Index: 1019195 (C4 (Web Text))

Max Activating Token Index: 97

Text #14

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0788. Min Act: -0.0000

Data Index: 1034117 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0784. Min Act: -0.0000

Data Index: 415947 (C4 (Web Text))

Max Activating Token Index: 369

Text #16

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0699. Min Act: -0.0000

Data Index: 499507 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0742. Min Act: -0.0000

Data Index: 986093 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0663. Min Act: -0.0000

Data Index: 1305376 (C4 (Web Text))

Max Activating Token Index: 415

Text #19

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0705. Min Act: -0.0000

Data Index: 756275 (C4 (Web Text))

Max Activating Token Index: 846