Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5764 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7822. Min Range: -0.7822

Max Act: 0.7822. Min Act: -0.0000

Data Index: 161494 (C4 (Web Text))

Max Activating Token Index: 575

Text #1

Max Range: 0.7822. Min Range: -0.7822

Max Act: 0.7556. Min Act: -0.0000

Data Index: 1171508 (C4 (Web Text))

Max Activating Token Index: 777

Text #2

Max Range: 0.7822. Min Range: -0.7822

Max Act: 0.7348. Min Act: -0.0000

Data Index: 96433 (C4 (Web Text))

Max Activating Token Index: 142

Text #3

Max Range: 0.7822. Min Range: -0.7822

Max Act: 0.6975. Min Act: -0.0000

Data Index: 631640 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 0.7822. Min Range: -0.7822

Max Act: 0.6639. Min Act: -0.0000

Data Index: 180207 (C4 (Web Text))

Max Activating Token Index: 252

Text #5

Max Range: 0.7822. Min Range: -0.7822

Max Act: 0.5921. Min Act: -0.0000

Data Index: 418746 (C4 (Web Text))

Max Activating Token Index: 381

Text #6

Max Range: 0.7822. Min Range: -0.7822

Max Act: 0.6037. Min Act: -0.0000

Data Index: 742177 (C4 (Web Text))

Max Activating Token Index: 925

Text #7

Max Range: 0.7822. Min Range: -0.7822

Max Act: 0.6007. Min Act: -0.0000

Data Index: 362454 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 0.7822. Min Range: -0.7822

Max Act: 0.5561. Min Act: -0.0000

Data Index: 167645 (C4 (Web Text))

Max Activating Token Index: 518

Text #9

Max Range: 0.7822. Min Range: -0.7822

Max Act: 0.5476. Min Act: -0.0000

Data Index: 1154370 (C4 (Web Text))

Max Activating Token Index: 908

Text #10

Max Range: 0.7822. Min Range: -0.7822

Max Act: 0.5434. Min Act: -0.0000

Data Index: 763099 (C4 (Web Text))

Max Activating Token Index: 897

Text #11

Max Range: 0.7822. Min Range: -0.7822

Max Act: 0.5177. Min Act: -0.0000

Data Index: 78740 (C4 (Web Text))

Max Activating Token Index: 750

Text #12

Max Range: 0.7822. Min Range: -0.7822

Max Act: 0.4803. Min Act: -0.0000

Data Index: 946426 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 0.7822. Min Range: -0.7822

Max Act: 0.4772. Min Act: -0.0000

Data Index: 1119609 (C4 (Web Text))

Max Activating Token Index: 302

Text #14

Max Range: 0.7822. Min Range: -0.7822

Max Act: 0.4740. Min Act: -0.0000

Data Index: 298899 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 0.7822. Min Range: -0.7822

Max Act: 0.4752. Min Act: -0.0000

Data Index: 651788 (C4 (Web Text))

Max Activating Token Index: 1010

Text #16

Max Range: 0.7822. Min Range: -0.7822

Max Act: 0.4726. Min Act: -0.0000

Data Index: 983696 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 0.7822. Min Range: -0.7822

Max Act: 0.4775. Min Act: -0.0000

Data Index: 219070 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 0.7822. Min Range: -0.7822

Max Act: 0.4605. Min Act: -0.0000

Data Index: 835032 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 0.7822. Min Range: -0.7822

Max Act: 0.4573. Min Act: -0.0000

Data Index: 399624 (C4 (Web Text))

Max Activating Token Index: 559