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

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

Neuron 3767 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5873. Min Range: -1.5873

Max Act: 1.5873. Min Act: -0.0001

Data Index: 641673 (C4 (Web Text))

Max Activating Token Index: 70

Text #1

Max Range: 1.5873. Min Range: -1.5873

Max Act: 1.1648. Min Act: -0.0001

Data Index: 604973 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 1.5873. Min Range: -1.5873

Max Act: 1.0762. Min Act: -0.0001

Data Index: 177089 (C4 (Web Text))

Max Activating Token Index: 82

Text #3

Max Range: 1.5873. Min Range: -1.5873

Max Act: 1.0887. Min Act: -0.0001

Data Index: 694301 (C4 (Web Text))

Max Activating Token Index: 678

Text #4

Max Range: 1.5873. Min Range: -1.5873

Max Act: 0.9608. Min Act: -0.0001

Data Index: 444349 (C4 (Web Text))

Max Activating Token Index: 344

Text #5

Max Range: 1.5873. Min Range: -1.5873

Max Act: 1.0004. Min Act: -0.0001

Data Index: 600788 (C4 (Web Text))

Max Activating Token Index: 475

Text #6

Max Range: 1.5873. Min Range: -1.5873

Max Act: 0.9469. Min Act: -0.0001

Data Index: 39554 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 1.5873. Min Range: -1.5873

Max Act: 0.9818. Min Act: -0.0001

Data Index: 1169080 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 1.5873. Min Range: -1.5873

Max Act: 0.9778. Min Act: -0.0001

Data Index: 283482 (C4 (Web Text))

Max Activating Token Index: 901

Text #9

Max Range: 1.5873. Min Range: -1.5873

Max Act: 0.9939. Min Act: -0.0001

Data Index: 557711 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 1.5873. Min Range: -1.5873

Max Act: 0.9874. Min Act: -0.0001

Data Index: 248757 (C4 (Web Text))

Max Activating Token Index: 562

Text #11

Max Range: 1.5873. Min Range: -1.5873

Max Act: 0.9112. Min Act: -0.0001

Data Index: 804067 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 1.5873. Min Range: -1.5873

Max Act: 1.0368. Min Act: -0.0001

Data Index: 309848 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 1.5873. Min Range: -1.5873

Max Act: 0.9426. Min Act: -0.0001

Data Index: 1294007 (C4 (Web Text))

Max Activating Token Index: 816

Text #14

Max Range: 1.5873. Min Range: -1.5873

Max Act: 0.8631. Min Act: -0.0001

Data Index: 731483 (C4 (Web Text))

Max Activating Token Index: 1011

Text #15

Max Range: 1.5873. Min Range: -1.5873

Max Act: 0.9013. Min Act: -0.0001

Data Index: 309098 (C4 (Web Text))

Max Activating Token Index: 184

Text #16

Max Range: 1.5873. Min Range: -1.5873

Max Act: 0.9063. Min Act: -0.0001

Data Index: 1050155 (C4 (Web Text))

Max Activating Token Index: 518

Text #17

Max Range: 1.5873. Min Range: -1.5873

Max Act: 0.8548. Min Act: -0.0001

Data Index: 267968 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 1.5873. Min Range: -1.5873

Max Act: 0.8537. Min Act: -0.0001

Data Index: 772514 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 1.5873. Min Range: -1.5873

Max Act: 0.8805. Min Act: -0.0001

Data Index: 41260 (C4 (Web Text))

Max Activating Token Index: 974