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

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

Neuron 1515 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: 0.1041. Min Range: -0.1041

Max Act: 0.0952. Min Act: -0.0001

Data Index: 453424 (C4 (Web Text))

Max Activating Token Index: 127

Text #1

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.1041. Min Act: -0.0001

Data Index: 1249746 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0865. Min Act: -0.0001

Data Index: 558304 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0844. Min Act: -0.0002

Data Index: 665599 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0875. Min Act: -0.0002

Data Index: 1104342 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0874. Min Act: -0.0002

Data Index: 1222213 (C4 (Web Text))

Max Activating Token Index: 664

Text #6

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0894. Min Act: -0.0001

Data Index: 207741 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0815. Min Act: -0.0001

Data Index: 1252280 (C4 (Web Text))

Max Activating Token Index: 952

Text #8

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0822. Min Act: -0.0001

Data Index: 360415 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0762. Min Act: -0.0002

Data Index: 493951 (C4 (Web Text))

Max Activating Token Index: 721

Text #10

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0787. Min Act: -0.0002

Data Index: 631443 (C4 (Web Text))

Max Activating Token Index: 259

Text #11

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0809. Min Act: -0.0002

Data Index: 1155 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0841. Min Act: -0.0002

Data Index: 165144 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0803. Min Act: -0.0001

Data Index: 653179 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0773. Min Act: -0.0002

Data Index: 1083232 (C4 (Web Text))

Max Activating Token Index: 157

Text #15

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0750. Min Act: -0.0002

Data Index: 792931 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0782. Min Act: -0.0001

Data Index: 985086 (C4 (Web Text))

Max Activating Token Index: 974

Text #17

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0728. Min Act: -0.0001

Data Index: 465854 (C4 (Web Text))

Max Activating Token Index: 338

Text #18

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0764. Min Act: -0.0002

Data Index: 710713 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0761. Min Act: -0.0002

Data Index: 623535 (C4 (Web Text))

Max Activating Token Index: 800