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

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

Neuron 2144 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.9384. Min Range: -1.9384

Max Act: 1.9384. Min Act: -0.0000

Data Index: 76200 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 1.9384. Min Range: -1.9384

Max Act: 1.8435. Min Act: -0.0000

Data Index: 467115 (C4 (Web Text))

Max Activating Token Index: 944

Text #2

Max Range: 1.9384. Min Range: -1.9384

Max Act: 1.8219. Min Act: -0.0000

Data Index: 1312232 (C4 (Web Text))

Max Activating Token Index: 966

Text #3

Max Range: 1.9384. Min Range: -1.9384

Max Act: 1.7988. Min Act: -0.0000

Data Index: 159205 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 1.9384. Min Range: -1.9384

Max Act: 1.7726. Min Act: -0.0000

Data Index: 960506 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 1.9384. Min Range: -1.9384

Max Act: 1.7326. Min Act: -0.0000

Data Index: 965487 (C4 (Web Text))

Max Activating Token Index: 422

Text #6

Max Range: 1.9384. Min Range: -1.9384

Max Act: 1.6321. Min Act: -0.0000

Data Index: 1635212 (Python Code)

Max Activating Token Index: 985

Text #7

Max Range: 1.9384. Min Range: -1.9384

Max Act: 1.6827. Min Act: -0.0000

Data Index: 639672 (C4 (Web Text))

Max Activating Token Index: 197

Text #8

Max Range: 1.9384. Min Range: -1.9384

Max Act: 1.6753. Min Act: -0.0000

Data Index: 881965 (C4 (Web Text))

Max Activating Token Index: 917

Text #9

Max Range: 1.9384. Min Range: -1.9384

Max Act: 1.6631. Min Act: -0.0000

Data Index: 349333 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 1.9384. Min Range: -1.9384

Max Act: 1.7189. Min Act: -0.0000

Data Index: 755711 (C4 (Web Text))

Max Activating Token Index: 264

Text #11

Max Range: 1.9384. Min Range: -1.9384

Max Act: 1.6242. Min Act: -0.0000

Data Index: 1059576 (C4 (Web Text))

Max Activating Token Index: 390

Text #12

Max Range: 1.9384. Min Range: -1.9384

Max Act: 1.6176. Min Act: -0.0000

Data Index: 926833 (C4 (Web Text))

Max Activating Token Index: 408

Text #13

Max Range: 1.9384. Min Range: -1.9384

Max Act: 1.6029. Min Act: -0.0000

Data Index: 203678 (C4 (Web Text))

Max Activating Token Index: 489

Text #14

Max Range: 1.9384. Min Range: -1.9384

Max Act: 1.6809. Min Act: -0.0000

Data Index: 483477 (C4 (Web Text))

Max Activating Token Index: 340

Text #15

Max Range: 1.9384. Min Range: -1.9384

Max Act: 1.5855. Min Act: -0.0000

Data Index: 352575 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 1.9384. Min Range: -1.9384

Max Act: 1.5892. Min Act: -0.0000

Data Index: 1044198 (C4 (Web Text))

Max Activating Token Index: 516

Text #17

Max Range: 1.9384. Min Range: -1.9384

Max Act: 1.5749. Min Act: -0.0000

Data Index: 410052 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 1.9384. Min Range: -1.9384

Max Act: 1.5686. Min Act: -0.0000

Data Index: 252141 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 1.9384. Min Range: -1.9384

Max Act: 1.4749. Min Act: -0.0000

Data Index: 605681 (C4 (Web Text))

Max Activating Token Index: 236