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

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

Neuron 2623 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9089. Min Range: -0.9089

Max Act: 0.9089. Min Act: -0.0000

Data Index: 840963 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 0.9089. Min Range: -0.9089

Max Act: 0.7014. Min Act: -0.0000

Data Index: 230418 (C4 (Web Text))

Max Activating Token Index: 467

Text #2

Max Range: 0.9089. Min Range: -0.9089

Max Act: 0.6176. Min Act: -0.0000

Data Index: 85720 (C4 (Web Text))

Max Activating Token Index: 157

Text #3

Max Range: 0.9089. Min Range: -0.9089

Max Act: 0.6447. Min Act: -0.0000

Data Index: 1303203 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 0.9089. Min Range: -0.9089

Max Act: 0.6314. Min Act: -0.0000

Data Index: 279236 (C4 (Web Text))

Max Activating Token Index: 754

Text #5

Max Range: 0.9089. Min Range: -0.9089

Max Act: 0.6246. Min Act: -0.0000

Data Index: 395025 (C4 (Web Text))

Max Activating Token Index: 957

Text #6

Max Range: 0.9089. Min Range: -0.9089

Max Act: 0.5609. Min Act: -0.0000

Data Index: 507635 (C4 (Web Text))

Max Activating Token Index: 806

Text #7

Max Range: 0.9089. Min Range: -0.9089

Max Act: 0.6102. Min Act: -0.0000

Data Index: 1342482 (C4 (Web Text))

Max Activating Token Index: 739

Text #8

Max Range: 0.9089. Min Range: -0.9089

Max Act: 0.5022. Min Act: -0.0000

Data Index: 1114337 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 0.9089. Min Range: -0.9089

Max Act: 0.5517. Min Act: -0.0000

Data Index: 608130 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 0.9089. Min Range: -0.9089

Max Act: 0.5930. Min Act: -0.0000

Data Index: 1236587 (C4 (Web Text))

Max Activating Token Index: 142

Text #11

Max Range: 0.9089. Min Range: -0.9089

Max Act: 0.5726. Min Act: -0.0000

Data Index: 201582 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 0.9089. Min Range: -0.9089

Max Act: 0.5925. Min Act: -0.0000

Data Index: 450793 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 0.9089. Min Range: -0.9089

Max Act: 0.5021. Min Act: -0.0000

Data Index: 449195 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 0.9089. Min Range: -0.9089

Max Act: 0.5169. Min Act: -0.0000

Data Index: 1128314 (C4 (Web Text))

Max Activating Token Index: 761

Text #15

Max Range: 0.9089. Min Range: -0.9089

Max Act: 0.5340. Min Act: -0.0000

Data Index: 793627 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 0.9089. Min Range: -0.9089

Max Act: 0.5477. Min Act: -0.0000

Data Index: 1098389 (C4 (Web Text))

Max Activating Token Index: 740

Text #17

Max Range: 0.9089. Min Range: -0.9089

Max Act: 0.5141. Min Act: -0.0000

Data Index: 496507 (C4 (Web Text))

Max Activating Token Index: 626

Text #18

Max Range: 0.9089. Min Range: -0.9089

Max Act: 0.5389. Min Act: -0.0000

Data Index: 222123 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 0.9089. Min Range: -0.9089

Max Act: 0.5364. Min Act: -0.0000

Data Index: 353640 (C4 (Web Text))

Max Activating Token Index: 494