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

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

Neuron 1307 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7548. Min Range: -2.7548

Max Act: 2.7548. Min Act: -0.0000

Data Index: 1140105 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 2.7548. Min Range: -2.7548

Max Act: 2.3870. Min Act: -0.0000

Data Index: 868169 (C4 (Web Text))

Max Activating Token Index: 207

Text #2

Max Range: 2.7548. Min Range: -2.7548

Max Act: 2.2085. Min Act: -0.0000

Data Index: 253447 (C4 (Web Text))

Max Activating Token Index: 269

Text #3

Max Range: 2.7548. Min Range: -2.7548

Max Act: 2.0006. Min Act: -0.0000

Data Index: 338735 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 2.7548. Min Range: -2.7548

Max Act: 1.6105. Min Act: -0.0000

Data Index: 1323386 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 2.7548. Min Range: -2.7548

Max Act: 2.0781. Min Act: -0.0000

Data Index: 600496 (C4 (Web Text))

Max Activating Token Index: 765

Text #6

Max Range: 2.7548. Min Range: -2.7548

Max Act: 1.8757. Min Act: -0.0000

Data Index: 267609 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 2.7548. Min Range: -2.7548

Max Act: 2.0780. Min Act: -0.0000

Data Index: 872715 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 2.7548. Min Range: -2.7548

Max Act: 2.0478. Min Act: -0.0000

Data Index: 1321849 (C4 (Web Text))

Max Activating Token Index: 399

Text #9

Max Range: 2.7548. Min Range: -2.7548

Max Act: 2.0144. Min Act: -0.0000

Data Index: 494227 (C4 (Web Text))

Max Activating Token Index: 602

Text #10

Max Range: 2.7548. Min Range: -2.7548

Max Act: 1.7860. Min Act: -0.0000

Data Index: 149916 (C4 (Web Text))

Max Activating Token Index: 670

Text #11

Max Range: 2.7548. Min Range: -2.7548

Max Act: 1.8660. Min Act: -0.0000

Data Index: 985149 (C4 (Web Text))

Max Activating Token Index: 833

Text #12

Max Range: 2.7548. Min Range: -2.7548

Max Act: 1.7058. Min Act: -0.0000

Data Index: 1358087 (C4 (Web Text))

Max Activating Token Index: 82

Text #13

Max Range: 2.7548. Min Range: -2.7548

Max Act: 1.7692. Min Act: -0.0000

Data Index: 49874 (C4 (Web Text))

Max Activating Token Index: 204

Text #14

Max Range: 2.7548. Min Range: -2.7548

Max Act: 1.7988. Min Act: -0.0000

Data Index: 104085 (C4 (Web Text))

Max Activating Token Index: 532

Text #15

Max Range: 2.7548. Min Range: -2.7548

Max Act: 1.6740. Min Act: -0.0000

Data Index: 766098 (C4 (Web Text))

Max Activating Token Index: 511

Text #16

Max Range: 2.7548. Min Range: -2.7548

Max Act: 1.5800. Min Act: -0.0000

Data Index: 883062 (C4 (Web Text))

Max Activating Token Index: 642

Text #17

Max Range: 2.7548. Min Range: -2.7548

Max Act: 1.7532. Min Act: -0.0000

Data Index: 773233 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 2.7548. Min Range: -2.7548

Max Act: 1.6915. Min Act: -0.0000

Data Index: 416639 (C4 (Web Text))

Max Activating Token Index: 618

Text #19

Max Range: 2.7548. Min Range: -2.7548

Max Act: 1.7017. Min Act: -0.0000

Data Index: 938822 (C4 (Web Text))

Max Activating Token Index: 198