Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2318 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.1068. Min Act: -0.0002

Data Index: 974927 (C4 (Web Text))

Max Activating Token Index: 588

Text #1

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.1108. Min Act: -0.0002

Data Index: 987523 (C4 (Web Text))

Max Activating Token Index: 543

Text #2

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0990. Min Act: -0.0002

Data Index: 1249263 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0961. Min Act: -0.0002

Data Index: 941351 (C4 (Web Text))

Max Activating Token Index: 195

Text #4

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.1037. Min Act: -0.0002

Data Index: 35982 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.1021. Min Act: -0.0002

Data Index: 284171 (C4 (Web Text))

Max Activating Token Index: 685

Text #6

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.1017. Min Act: -0.0002

Data Index: 1296301 (C4 (Web Text))

Max Activating Token Index: 512

Text #7

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.1000. Min Act: -0.0002

Data Index: 194427 (C4 (Web Text))

Max Activating Token Index: 591

Text #8

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0956. Min Act: -0.0002

Data Index: 1195101 (C4 (Web Text))

Max Activating Token Index: 289

Text #9

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0953. Min Act: -0.0002

Data Index: 938218 (C4 (Web Text))

Max Activating Token Index: 423

Text #10

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0935. Min Act: -0.0002

Data Index: 943701 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0931. Min Act: -0.0002

Data Index: 556536 (C4 (Web Text))

Max Activating Token Index: 894

Text #12

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0898. Min Act: -0.0002

Data Index: 357697 (C4 (Web Text))

Max Activating Token Index: 509

Text #13

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0911. Min Act: -0.0002

Data Index: 707233 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0914. Min Act: -0.0002

Data Index: 928218 (C4 (Web Text))

Max Activating Token Index: 908

Text #15

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0930. Min Act: -0.0002

Data Index: 1053569 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0861. Min Act: -0.0002

Data Index: 688531 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0875. Min Act: -0.0002

Data Index: 1025649 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0886. Min Act: -0.0002

Data Index: 509131 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0801. Min Act: -0.0002

Data Index: 188309 (C4 (Web Text))

Max Activating Token Index: 531