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

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

Neuron 1575 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.9575. Min Act: -0.0000

Data Index: 1054654 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.9038. Min Act: -0.0000

Data Index: 356570 (C4 (Web Text))

Max Activating Token Index: 978

Text #2

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.7852. Min Act: -0.0000

Data Index: 140801 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.7634. Min Act: -0.0000

Data Index: 1100477 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.5739. Min Act: -0.0000

Data Index: 361731 (C4 (Web Text))

Max Activating Token Index: 278

Text #5

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.7066. Min Act: -0.0000

Data Index: 935950 (C4 (Web Text))

Max Activating Token Index: 960

Text #6

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.6169. Min Act: -0.0000

Data Index: 1079862 (C4 (Web Text))

Max Activating Token Index: 741

Text #7

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.6499. Min Act: -0.0000

Data Index: 341756 (C4 (Web Text))

Max Activating Token Index: 228

Text #8

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.6674. Min Act: -0.0000

Data Index: 1012989 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.5720. Min Act: -0.0000

Data Index: 138490 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.6122. Min Act: -0.0000

Data Index: 659386 (C4 (Web Text))

Max Activating Token Index: 579

Text #11

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.5721. Min Act: -0.0000

Data Index: 954169 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.6200. Min Act: -0.0000

Data Index: 470144 (C4 (Web Text))

Max Activating Token Index: 218

Text #13

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.6062. Min Act: -0.0000

Data Index: 1080697 (C4 (Web Text))

Max Activating Token Index: 498

Text #14

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.5977. Min Act: -0.0000

Data Index: 1150612 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.5722. Min Act: -0.0000

Data Index: 837604 (C4 (Web Text))

Max Activating Token Index: 389

Text #16

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.5844. Min Act: -0.0000

Data Index: 818350 (C4 (Web Text))

Max Activating Token Index: 257

Text #17

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.6091. Min Act: -0.0000

Data Index: 449974 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.5694. Min Act: -0.0000

Data Index: 493232 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.5542. Min Act: -0.0000

Data Index: 858657 (C4 (Web Text))

Max Activating Token Index: 815