Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1682 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1144. Min Act: -0.0003

Data Index: 42981 (C4 (Web Text))

Max Activating Token Index: 309

Text #1

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1003. Min Act: -0.0003

Data Index: 266269 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0907. Min Act: -0.0003

Data Index: 174119 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0935. Min Act: -0.0003

Data Index: 978537 (C4 (Web Text))

Max Activating Token Index: 962

Text #4

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0905. Min Act: -0.0003

Data Index: 1036153 (C4 (Web Text))

Max Activating Token Index: 437

Text #5

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0958. Min Act: -0.0003

Data Index: 94795 (C4 (Web Text))

Max Activating Token Index: 694

Text #6

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0864. Min Act: -0.0003

Data Index: 655011 (C4 (Web Text))

Max Activating Token Index: 844

Text #7

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0871. Min Act: -0.0003

Data Index: 669658 (C4 (Web Text))

Max Activating Token Index: 706

Text #8

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0808. Min Act: -0.0003

Data Index: 598744 (C4 (Web Text))

Max Activating Token Index: 971

Text #9

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0757. Min Act: -0.0003

Data Index: 76670 (C4 (Web Text))

Max Activating Token Index: 840

Text #10

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0819. Min Act: -0.0003

Data Index: 544467 (C4 (Web Text))

Max Activating Token Index: 939

Text #11

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0739. Min Act: -0.0003

Data Index: 647733 (C4 (Web Text))

Max Activating Token Index: 240

Text #12

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0788. Min Act: -0.0003

Data Index: 240046 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0816. Min Act: -0.0003

Data Index: 665966 (C4 (Web Text))

Max Activating Token Index: 538

Text #14

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0781. Min Act: -0.0003

Data Index: 1019655 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0724. Min Act: -0.0003

Data Index: 239857 (C4 (Web Text))

Max Activating Token Index: 669

Text #16

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0748. Min Act: -0.0003

Data Index: 1131642 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0788. Min Act: -0.0003

Data Index: 738646 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0659. Min Act: -0.0003

Data Index: 904315 (C4 (Web Text))

Max Activating Token Index: 589

Text #19

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0757. Min Act: -0.0003

Data Index: 386850 (C4 (Web Text))

Max Activating Token Index: 462