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

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

Neuron 3550 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: 0.0938. Min Range: -0.0938

Max Act: 0.0905. Min Act: -0.0001

Data Index: 582915 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0938. Min Act: -0.0002

Data Index: 832464 (C4 (Web Text))

Max Activating Token Index: 206

Text #2

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0809. Min Act: -0.0001

Data Index: 863502 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0832. Min Act: -0.0002

Data Index: 438600 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0799. Min Act: -0.0001

Data Index: 78259 (C4 (Web Text))

Max Activating Token Index: 864

Text #5

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0763. Min Act: -0.0001

Data Index: 605490 (C4 (Web Text))

Max Activating Token Index: 546

Text #6

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0754. Min Act: -0.0002

Data Index: 841761 (C4 (Web Text))

Max Activating Token Index: 155

Text #7

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0687. Min Act: -0.0002

Data Index: 1351223 (C4 (Web Text))

Max Activating Token Index: 728

Text #8

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0770. Min Act: -0.0001

Data Index: 734045 (C4 (Web Text))

Max Activating Token Index: 431

Text #9

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0716. Min Act: -0.0001

Data Index: 1221822 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0737. Min Act: -0.0002

Data Index: 1065180 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0720. Min Act: -0.0002

Data Index: 813869 (C4 (Web Text))

Max Activating Token Index: 714

Text #12

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0739. Min Act: -0.0002

Data Index: 511441 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0684. Min Act: -0.0001

Data Index: 313547 (C4 (Web Text))

Max Activating Token Index: 209

Text #14

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0681. Min Act: -0.0002

Data Index: 457592 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0710. Min Act: -0.0001

Data Index: 717859 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0690. Min Act: -0.0002

Data Index: 411181 (C4 (Web Text))

Max Activating Token Index: 197

Text #17

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0666. Min Act: -0.0001

Data Index: 1098110 (C4 (Web Text))

Max Activating Token Index: 267

Text #18

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0757. Min Act: -0.0002

Data Index: 409181 (C4 (Web Text))

Max Activating Token Index: 546

Text #19

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0726. Min Act: -0.0002

Data Index: 163408 (C4 (Web Text))

Max Activating Token Index: 822