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

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

Neuron 4596 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0733. Min Act: -0.0001

Data Index: 1199342 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0603. Min Act: -0.0001

Data Index: 357169 (C4 (Web Text))

Max Activating Token Index: 722

Text #2

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0609. Min Act: -0.0001

Data Index: 883461 (C4 (Web Text))

Max Activating Token Index: 249

Text #3

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0592. Min Act: -0.0001

Data Index: 1344005 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0521. Min Act: -0.0001

Data Index: 211693 (C4 (Web Text))

Max Activating Token Index: 875

Text #5

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0517. Min Act: -0.0001

Data Index: 1050761 (C4 (Web Text))

Max Activating Token Index: 856

Text #6

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0590. Min Act: -0.0001

Data Index: 399427 (C4 (Web Text))

Max Activating Token Index: 390

Text #7

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0525. Min Act: -0.0001

Data Index: 833849 (C4 (Web Text))

Max Activating Token Index: 793

Text #8

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0515. Min Act: -0.0001

Data Index: 639127 (C4 (Web Text))

Max Activating Token Index: 1019

Text #9

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0533. Min Act: -0.0001

Data Index: 864624 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0537. Min Act: -0.0001

Data Index: 780437 (C4 (Web Text))

Max Activating Token Index: 183

Text #11

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0484. Min Act: -0.0001

Data Index: 84102 (C4 (Web Text))

Max Activating Token Index: 105

Text #12

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0437. Min Act: -0.0001

Data Index: 1256932 (C4 (Web Text))

Max Activating Token Index: 696

Text #13

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0519. Min Act: -0.0001

Data Index: 802610 (C4 (Web Text))

Max Activating Token Index: 571

Text #14

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0495. Min Act: -0.0001

Data Index: 257087 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0539. Min Act: -0.0001

Data Index: 212399 (C4 (Web Text))

Max Activating Token Index: 228

Text #16

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0506. Min Act: -0.0001

Data Index: 512876 (C4 (Web Text))

Max Activating Token Index: 934

Text #17

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0478. Min Act: -0.0001

Data Index: 568917 (C4 (Web Text))

Max Activating Token Index: 228

Text #18

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0511. Min Act: -0.0001

Data Index: 348107 (C4 (Web Text))

Max Activating Token Index: 106

Text #19

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0489. Min Act: -0.0001

Data Index: 1358246 (C4 (Web Text))

Max Activating Token Index: 491