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

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

Neuron 3713 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5966. Min Range: -3.5966

Max Act: 3.5966. Min Act: -0.0000

Data Index: 165694 (C4 (Web Text))

Max Activating Token Index: 480

Text #1

Max Range: 3.5966. Min Range: -3.5966

Max Act: 3.3874. Min Act: -0.0000

Data Index: 251375 (C4 (Web Text))

Max Activating Token Index: 851

Text #2

Max Range: 3.5966. Min Range: -3.5966

Max Act: 3.0798. Min Act: -0.0000

Data Index: 1305484 (C4 (Web Text))

Max Activating Token Index: 496

Text #3

Max Range: 3.5966. Min Range: -3.5966

Max Act: 3.2732. Min Act: -0.0000

Data Index: 942688 (C4 (Web Text))

Max Activating Token Index: 966

Text #4

Max Range: 3.5966. Min Range: -3.5966

Max Act: 3.2608. Min Act: -0.0000

Data Index: 174709 (C4 (Web Text))

Max Activating Token Index: 724

Text #5

Max Range: 3.5966. Min Range: -3.5966

Max Act: 3.2642. Min Act: -0.0000

Data Index: 532341 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 3.5966. Min Range: -3.5966

Max Act: 3.2349. Min Act: -0.0000

Data Index: 947286 (C4 (Web Text))

Max Activating Token Index: 457

Text #7

Max Range: 3.5966. Min Range: -3.5966

Max Act: 3.2186. Min Act: -0.0000

Data Index: 257939 (C4 (Web Text))

Max Activating Token Index: 985

Text #8

Max Range: 3.5966. Min Range: -3.5966

Max Act: 3.2757. Min Act: -0.0000

Data Index: 135736 (C4 (Web Text))

Max Activating Token Index: 318

Text #9

Max Range: 3.5966. Min Range: -3.5966

Max Act: 2.8574. Min Act: -0.0000

Data Index: 244437 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 3.5966. Min Range: -3.5966

Max Act: 2.8779. Min Act: -0.0000

Data Index: 432639 (C4 (Web Text))

Max Activating Token Index: 957

Text #11

Max Range: 3.5966. Min Range: -3.5966

Max Act: 2.9999. Min Act: -0.0000

Data Index: 316026 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 3.5966. Min Range: -3.5966

Max Act: 3.0107. Min Act: -0.0000

Data Index: 974567 (C4 (Web Text))

Max Activating Token Index: 302

Text #13

Max Range: 3.5966. Min Range: -3.5966

Max Act: 2.8503. Min Act: -0.0000

Data Index: 708733 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 3.5966. Min Range: -3.5966

Max Act: 2.8513. Min Act: -0.0000

Data Index: 35721 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 3.5966. Min Range: -3.5966

Max Act: 2.9274. Min Act: -0.0000

Data Index: 881699 (C4 (Web Text))

Max Activating Token Index: 859

Text #16

Max Range: 3.5966. Min Range: -3.5966

Max Act: 3.2003. Min Act: -0.0000

Data Index: 632286 (C4 (Web Text))

Max Activating Token Index: 748

Text #17

Max Range: 3.5966. Min Range: -3.5966

Max Act: 2.9221. Min Act: -0.0000

Data Index: 97564 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 3.5966. Min Range: -3.5966

Max Act: 2.9177. Min Act: -0.0000

Data Index: 166467 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 3.5966. Min Range: -3.5966

Max Act: 2.6852. Min Act: -0.0000

Data Index: 1062967 (C4 (Web Text))

Max Activating Token Index: 899