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

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

Neuron 2423 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9692. Min Range: -1.9692

Max Act: 1.9692. Min Act: -0.0000

Data Index: 28014 (C4 (Web Text))

Max Activating Token Index: 551

Text #1

Max Range: 1.9692. Min Range: -1.9692

Max Act: 1.9090. Min Act: -0.0000

Data Index: 1218727 (C4 (Web Text))

Max Activating Token Index: 311

Text #2

Max Range: 1.9692. Min Range: -1.9692

Max Act: 1.3176. Min Act: -0.0000

Data Index: 479317 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 1.9692. Min Range: -1.9692

Max Act: 1.2718. Min Act: -0.0000

Data Index: 470210 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 1.9692. Min Range: -1.9692

Max Act: 1.0715. Min Act: -0.0000

Data Index: 868064 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 1.9692. Min Range: -1.9692

Max Act: 1.0886. Min Act: -0.0000

Data Index: 438056 (C4 (Web Text))

Max Activating Token Index: 871

Text #6

Max Range: 1.9692. Min Range: -1.9692

Max Act: 1.0499. Min Act: -0.0000

Data Index: 926060 (C4 (Web Text))

Max Activating Token Index: 677

Text #7

Max Range: 1.9692. Min Range: -1.9692

Max Act: 1.1152. Min Act: -0.0000

Data Index: 477266 (C4 (Web Text))

Max Activating Token Index: 346

Text #8

Max Range: 1.9692. Min Range: -1.9692

Max Act: 1.1100. Min Act: -0.0000

Data Index: 1301262 (C4 (Web Text))

Max Activating Token Index: 158

Text #9

Max Range: 1.9692. Min Range: -1.9692

Max Act: 1.0321. Min Act: -0.0000

Data Index: 419593 (C4 (Web Text))

Max Activating Token Index: 889

Text #10

Max Range: 1.9692. Min Range: -1.9692

Max Act: 1.1710. Min Act: -0.0000

Data Index: 884369 (C4 (Web Text))

Max Activating Token Index: 599

Text #11

Max Range: 1.9692. Min Range: -1.9692

Max Act: 0.9853. Min Act: -0.0000

Data Index: 1129362 (C4 (Web Text))

Max Activating Token Index: 189

Text #12

Max Range: 1.9692. Min Range: -1.9692

Max Act: 0.9744. Min Act: -0.0000

Data Index: 113990 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 1.9692. Min Range: -1.9692

Max Act: 0.8953. Min Act: -0.0000

Data Index: 784635 (C4 (Web Text))

Max Activating Token Index: 938

Text #14

Max Range: 1.9692. Min Range: -1.9692

Max Act: 0.8547. Min Act: -0.0000

Data Index: 1224305 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 1.9692. Min Range: -1.9692

Max Act: 0.9857. Min Act: -0.0000

Data Index: 343512 (C4 (Web Text))

Max Activating Token Index: 1011

Text #16

Max Range: 1.9692. Min Range: -1.9692

Max Act: 0.8999. Min Act: -0.0000

Data Index: 587656 (C4 (Web Text))

Max Activating Token Index: 396

Text #17

Max Range: 1.9692. Min Range: -1.9692

Max Act: 0.8314. Min Act: -0.0000

Data Index: 539496 (C4 (Web Text))

Max Activating Token Index: 779

Text #18

Max Range: 1.9692. Min Range: -1.9692

Max Act: 0.9001. Min Act: -0.0000

Data Index: 69933 (C4 (Web Text))

Max Activating Token Index: 104

Text #19

Max Range: 1.9692. Min Range: -1.9692

Max Act: 0.8413. Min Act: -0.0000

Data Index: 970361 (C4 (Web Text))

Max Activating Token Index: 94