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

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

Neuron 3379 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0851. Min Range: -1.0851

Max Act: 1.0851. Min Act: -0.0001

Data Index: 929571 (C4 (Web Text))

Max Activating Token Index: 454

Text #1

Max Range: 1.0851. Min Range: -1.0851

Max Act: 0.8895. Min Act: -0.0001

Data Index: 458053 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 1.0851. Min Range: -1.0851

Max Act: 1.0521. Min Act: -0.0001

Data Index: 198463 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 1.0851. Min Range: -1.0851

Max Act: 0.9710. Min Act: -0.0001

Data Index: 121593 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 1.0851. Min Range: -1.0851

Max Act: 1.0016. Min Act: -0.0001

Data Index: 217476 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 1.0851. Min Range: -1.0851

Max Act: 1.0006. Min Act: -0.0001

Data Index: 1355505 (C4 (Web Text))

Max Activating Token Index: 170

Text #6

Max Range: 1.0851. Min Range: -1.0851

Max Act: 0.8819. Min Act: -0.0001

Data Index: 227780 (C4 (Web Text))

Max Activating Token Index: 326

Text #7

Max Range: 1.0851. Min Range: -1.0851

Max Act: 0.9753. Min Act: -0.0001

Data Index: 306365 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 1.0851. Min Range: -1.0851

Max Act: 0.9098. Min Act: -0.0001

Data Index: 60829 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 1.0851. Min Range: -1.0851

Max Act: 0.9726. Min Act: -0.0001

Data Index: 738673 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 1.0851. Min Range: -1.0851

Max Act: 0.9623. Min Act: -0.0001

Data Index: 1192893 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 1.0851. Min Range: -1.0851

Max Act: 0.7795. Min Act: -0.0001

Data Index: 860506 (C4 (Web Text))

Max Activating Token Index: 270

Text #12

Max Range: 1.0851. Min Range: -1.0851

Max Act: 0.8766. Min Act: -0.0001

Data Index: 178572 (C4 (Web Text))

Max Activating Token Index: 569

Text #13

Max Range: 1.0851. Min Range: -1.0851

Max Act: 0.9151. Min Act: -0.0001

Data Index: 633514 (C4 (Web Text))

Max Activating Token Index: 486

Text #14

Max Range: 1.0851. Min Range: -1.0851

Max Act: 0.9341. Min Act: -0.0001

Data Index: 1049518 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 1.0851. Min Range: -1.0851

Max Act: 0.8741. Min Act: -0.0001

Data Index: 857612 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 1.0851. Min Range: -1.0851

Max Act: 0.9312. Min Act: -0.0001

Data Index: 790079 (C4 (Web Text))

Max Activating Token Index: 694

Text #17

Max Range: 1.0851. Min Range: -1.0851

Max Act: 0.8280. Min Act: -0.0001

Data Index: 1031312 (C4 (Web Text))

Max Activating Token Index: 511

Text #18

Max Range: 1.0851. Min Range: -1.0851

Max Act: 0.8532. Min Act: -0.0001

Data Index: 789069 (C4 (Web Text))

Max Activating Token Index: 497

Text #19

Max Range: 1.0851. Min Range: -1.0851

Max Act: 0.9232. Min Act: -0.0001

Data Index: 578062 (C4 (Web Text))

Max Activating Token Index: 249