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

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

Neuron 5220 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0316. Min Range: -4.0316

Max Act: 4.0316. Min Act: -0.0000

Data Index: 247387 (C4 (Web Text))

Max Activating Token Index: 165

Text #1

Max Range: 4.0316. Min Range: -4.0316

Max Act: 3.9719. Min Act: -0.0000

Data Index: 923625 (C4 (Web Text))

Max Activating Token Index: 605

Text #2

Max Range: 4.0316. Min Range: -4.0316

Max Act: 3.7019. Min Act: -0.0000

Data Index: 497743 (C4 (Web Text))

Max Activating Token Index: 835

Text #3

Max Range: 4.0316. Min Range: -4.0316

Max Act: 3.3587. Min Act: -0.0000

Data Index: 963511 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 4.0316. Min Range: -4.0316

Max Act: 3.3495. Min Act: -0.0000

Data Index: 1171231 (C4 (Web Text))

Max Activating Token Index: 688

Text #5

Max Range: 4.0316. Min Range: -4.0316

Max Act: 3.5760. Min Act: -0.0000

Data Index: 252293 (C4 (Web Text))

Max Activating Token Index: 757

Text #6

Max Range: 4.0316. Min Range: -4.0316

Max Act: 3.5260. Min Act: -0.0000

Data Index: 914906 (C4 (Web Text))

Max Activating Token Index: 738

Text #7

Max Range: 4.0316. Min Range: -4.0316

Max Act: 3.5022. Min Act: -0.0000

Data Index: 846705 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 4.0316. Min Range: -4.0316

Max Act: 3.2713. Min Act: -0.0000

Data Index: 347003 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 4.0316. Min Range: -4.0316

Max Act: 3.2625. Min Act: -0.0000

Data Index: 575 (C4 (Web Text))

Max Activating Token Index: 1018

Text #10

Max Range: 4.0316. Min Range: -4.0316

Max Act: 3.2146. Min Act: -0.0000

Data Index: 17279 (C4 (Web Text))

Max Activating Token Index: 478

Text #11

Max Range: 4.0316. Min Range: -4.0316

Max Act: 3.2152. Min Act: -0.0000

Data Index: 984435 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 4.0316. Min Range: -4.0316

Max Act: 3.0748. Min Act: -0.0000

Data Index: 792598 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 4.0316. Min Range: -4.0316

Max Act: 3.2127. Min Act: -0.0000

Data Index: 1213788 (C4 (Web Text))

Max Activating Token Index: 13

Text #14

Max Range: 4.0316. Min Range: -4.0316

Max Act: 3.1981. Min Act: -0.0000

Data Index: 608049 (C4 (Web Text))

Max Activating Token Index: 389

Text #15

Max Range: 4.0316. Min Range: -4.0316

Max Act: 3.3546. Min Act: -0.0000

Data Index: 1192914 (C4 (Web Text))

Max Activating Token Index: 499

Text #16

Max Range: 4.0316. Min Range: -4.0316

Max Act: 3.1852. Min Act: -0.0000

Data Index: 977661 (C4 (Web Text))

Max Activating Token Index: 963

Text #17

Max Range: 4.0316. Min Range: -4.0316

Max Act: 2.8044. Min Act: -0.0000

Data Index: 685518 (C4 (Web Text))

Max Activating Token Index: 849

Text #18

Max Range: 4.0316. Min Range: -4.0316

Max Act: 3.1918. Min Act: -0.0000

Data Index: 761297 (C4 (Web Text))

Max Activating Token Index: 21

Text #19

Max Range: 4.0316. Min Range: -4.0316

Max Act: 3.0218. Min Act: -0.0000

Data Index: 336945 (C4 (Web Text))

Max Activating Token Index: 270