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

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

Neuron 3653 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: 1.0456. Min Range: -1.0456

Max Act: 1.0456. Min Act: -0.0000

Data Index: 121468 (C4 (Web Text))

Max Activating Token Index: 916

Text #1

Max Range: 1.0456. Min Range: -1.0456

Max Act: 0.9078. Min Act: -0.0000

Data Index: 792743 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 1.0456. Min Range: -1.0456

Max Act: 0.8384. Min Act: -0.0000

Data Index: 9470 (C4 (Web Text))

Max Activating Token Index: 557

Text #3

Max Range: 1.0456. Min Range: -1.0456

Max Act: 0.8631. Min Act: -0.0000

Data Index: 285900 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 1.0456. Min Range: -1.0456

Max Act: 0.7998. Min Act: -0.0000

Data Index: 482619 (C4 (Web Text))

Max Activating Token Index: 258

Text #5

Max Range: 1.0456. Min Range: -1.0456

Max Act: 0.7932. Min Act: -0.0000

Data Index: 329492 (C4 (Web Text))

Max Activating Token Index: 995

Text #6

Max Range: 1.0456. Min Range: -1.0456

Max Act: 0.7901. Min Act: -0.0000

Data Index: 699083 (C4 (Web Text))

Max Activating Token Index: 809

Text #7

Max Range: 1.0456. Min Range: -1.0456

Max Act: 0.7746. Min Act: -0.0000

Data Index: 1150289 (C4 (Web Text))

Max Activating Token Index: 213

Text #8

Max Range: 1.0456. Min Range: -1.0456

Max Act: 0.7253. Min Act: -0.0000

Data Index: 1219214 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 1.0456. Min Range: -1.0456

Max Act: 0.7800. Min Act: -0.0000

Data Index: 900284 (C4 (Web Text))

Max Activating Token Index: 48

Text #10

Max Range: 1.0456. Min Range: -1.0456

Max Act: 0.7416. Min Act: -0.0000

Data Index: 636495 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 1.0456. Min Range: -1.0456

Max Act: 0.7663. Min Act: -0.0000

Data Index: 779831 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 1.0456. Min Range: -1.0456

Max Act: 0.7578. Min Act: -0.0000

Data Index: 732321 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 1.0456. Min Range: -1.0456

Max Act: 0.7364. Min Act: -0.0000

Data Index: 370365 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 1.0456. Min Range: -1.0456

Max Act: 0.7013. Min Act: -0.0000

Data Index: 1604510 (Python Code)

Max Activating Token Index: 64

Text #15

Max Range: 1.0456. Min Range: -1.0456

Max Act: 0.7029. Min Act: -0.0000

Data Index: 943791 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 1.0456. Min Range: -1.0456

Max Act: 0.7212. Min Act: -0.0000

Data Index: 309865 (C4 (Web Text))

Max Activating Token Index: 341

Text #17

Max Range: 1.0456. Min Range: -1.0456

Max Act: 0.6675. Min Act: -0.0000

Data Index: 574964 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 1.0456. Min Range: -1.0456

Max Act: 0.6832. Min Act: -0.0000

Data Index: 52463 (C4 (Web Text))

Max Activating Token Index: 918

Text #19

Max Range: 1.0456. Min Range: -1.0456

Max Act: 0.7065. Min Act: -0.0000

Data Index: 175935 (C4 (Web Text))

Max Activating Token Index: 221