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

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

Neuron 2164 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0755. Min Range: -1.0755

Max Act: 1.0351. Min Act: -0.0003

Data Index: 585237 (C4 (Web Text))

Max Activating Token Index: 659

Text #1

Max Range: 1.0755. Min Range: -1.0755

Max Act: 1.0755. Min Act: -0.0003

Data Index: 78044 (C4 (Web Text))

Max Activating Token Index: 595

Text #2

Max Range: 1.0755. Min Range: -1.0755

Max Act: 0.9562. Min Act: -0.0003

Data Index: 1286110 (C4 (Web Text))

Max Activating Token Index: 918

Text #3

Max Range: 1.0755. Min Range: -1.0755

Max Act: 0.9769. Min Act: -0.0003

Data Index: 1340878 (C4 (Web Text))

Max Activating Token Index: 434

Text #4

Max Range: 1.0755. Min Range: -1.0755

Max Act: 0.9191. Min Act: -0.0003

Data Index: 1233396 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 1.0755. Min Range: -1.0755

Max Act: 0.9438. Min Act: -0.0003

Data Index: 621191 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 1.0755. Min Range: -1.0755

Max Act: 0.9376. Min Act: -0.0003

Data Index: 7773 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 1.0755. Min Range: -1.0755

Max Act: 0.8453. Min Act: -0.0003

Data Index: 699256 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 1.0755. Min Range: -1.0755

Max Act: 0.9110. Min Act: -0.0003

Data Index: 879176 (C4 (Web Text))

Max Activating Token Index: 504

Text #9

Max Range: 1.0755. Min Range: -1.0755

Max Act: 0.8751. Min Act: -0.0003

Data Index: 1055724 (C4 (Web Text))

Max Activating Token Index: 796

Text #10

Max Range: 1.0755. Min Range: -1.0755

Max Act: 0.7745. Min Act: -0.0003

Data Index: 763222 (C4 (Web Text))

Max Activating Token Index: 756

Text #11

Max Range: 1.0755. Min Range: -1.0755

Max Act: 0.7941. Min Act: -0.0003

Data Index: 942185 (C4 (Web Text))

Max Activating Token Index: 394

Text #12

Max Range: 1.0755. Min Range: -1.0755

Max Act: 0.8192. Min Act: -0.0003

Data Index: 389222 (C4 (Web Text))

Max Activating Token Index: 798

Text #13

Max Range: 1.0755. Min Range: -1.0755

Max Act: 0.8099. Min Act: -0.0003

Data Index: 1031688 (C4 (Web Text))

Max Activating Token Index: 738

Text #14

Max Range: 1.0755. Min Range: -1.0755

Max Act: 0.8351. Min Act: -0.0003

Data Index: 505723 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 1.0755. Min Range: -1.0755

Max Act: 0.8033. Min Act: -0.0003

Data Index: 852496 (C4 (Web Text))

Max Activating Token Index: 338

Text #16

Max Range: 1.0755. Min Range: -1.0755

Max Act: 0.7964. Min Act: -0.0003

Data Index: 1208729 (C4 (Web Text))

Max Activating Token Index: 995

Text #17

Max Range: 1.0755. Min Range: -1.0755

Max Act: 0.7718. Min Act: -0.0003

Data Index: 801538 (C4 (Web Text))

Max Activating Token Index: 863

Text #18

Max Range: 1.0755. Min Range: -1.0755

Max Act: 0.8203. Min Act: -0.0003

Data Index: 714880 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 1.0755. Min Range: -1.0755

Max Act: 0.8090. Min Act: -0.0003

Data Index: 678122 (C4 (Web Text))

Max Activating Token Index: 481