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

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

Neuron 2004 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5089. Min Range: -5.5089

Max Act: 4.8573. Min Act: -0.0000

Data Index: 1136432 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 5.5089. Min Range: -5.5089

Max Act: 5.3331. Min Act: -0.0001

Data Index: 627177 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 5.5089. Min Range: -5.5089

Max Act: 5.5089. Min Act: -0.0001

Data Index: 1208468 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 5.5089. Min Range: -5.5089

Max Act: 5.2631. Min Act: -0.0000

Data Index: 1259898 (C4 (Web Text))

Max Activating Token Index: 893

Text #4

Max Range: 5.5089. Min Range: -5.5089

Max Act: 5.4827. Min Act: -0.0001

Data Index: 1315868 (C4 (Web Text))

Max Activating Token Index: 616

Text #5

Max Range: 5.5089. Min Range: -5.5089

Max Act: 4.8869. Min Act: -0.0000

Data Index: 666894 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 5.5089. Min Range: -5.5089

Max Act: 4.9634. Min Act: -0.0000

Data Index: 1191603 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 5.5089. Min Range: -5.5089

Max Act: 4.9784. Min Act: -0.0000

Data Index: 100441 (C4 (Web Text))

Max Activating Token Index: 782

Text #8

Max Range: 5.5089. Min Range: -5.5089

Max Act: 4.7019. Min Act: -0.0000

Data Index: 1193424 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 5.5089. Min Range: -5.5089

Max Act: 4.9379. Min Act: -0.0000

Data Index: 147043 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 5.5089. Min Range: -5.5089

Max Act: 4.9383. Min Act: -0.0000

Data Index: 1024797 (C4 (Web Text))

Max Activating Token Index: 302

Text #11

Max Range: 5.5089. Min Range: -5.5089

Max Act: 4.8670. Min Act: -0.0000

Data Index: 69000 (C4 (Web Text))

Max Activating Token Index: 834

Text #12

Max Range: 5.5089. Min Range: -5.5089

Max Act: 4.7103. Min Act: -0.0001

Data Index: 748843 (C4 (Web Text))

Max Activating Token Index: 53

Text #13

Max Range: 5.5089. Min Range: -5.5089

Max Act: 4.8343. Min Act: -0.0000

Data Index: 939723 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 5.5089. Min Range: -5.5089

Max Act: 4.6252. Min Act: -0.0000

Data Index: 1280276 (C4 (Web Text))

Max Activating Token Index: 423

Text #15

Max Range: 5.5089. Min Range: -5.5089

Max Act: 4.7611. Min Act: -0.0000

Data Index: 1020609 (C4 (Web Text))

Max Activating Token Index: 378

Text #16

Max Range: 5.5089. Min Range: -5.5089

Max Act: 4.8967. Min Act: -0.0000

Data Index: 407278 (C4 (Web Text))

Max Activating Token Index: 681

Text #17

Max Range: 5.5089. Min Range: -5.5089

Max Act: 4.6239. Min Act: -0.0001

Data Index: 437856 (C4 (Web Text))

Max Activating Token Index: 846

Text #18

Max Range: 5.5089. Min Range: -5.5089

Max Act: 4.8033. Min Act: -0.0000

Data Index: 726551 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 5.5089. Min Range: -5.5089

Max Act: 4.6245. Min Act: -0.0001

Data Index: 477048 (C4 (Web Text))

Max Activating Token Index: 18