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

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

Neuron 4654 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.7214. Min Act: -0.0000

Data Index: 1227186 (C4 (Web Text))

Max Activating Token Index: 462

Text #1

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.6064. Min Act: -0.0000

Data Index: 121942 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.5757. Min Act: -0.0000

Data Index: 809942 (C4 (Web Text))

Max Activating Token Index: 304

Text #3

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.4979. Min Act: -0.0000

Data Index: 779682 (C4 (Web Text))

Max Activating Token Index: 465

Text #4

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.5029. Min Act: -0.0000

Data Index: 1099940 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.5001. Min Act: -0.0000

Data Index: 318397 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.4915. Min Act: -0.0000

Data Index: 426631 (C4 (Web Text))

Max Activating Token Index: 404

Text #7

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.5006. Min Act: 0.0000

Data Index: 936529 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.4654. Min Act: -0.0000

Data Index: 956076 (C4 (Web Text))

Max Activating Token Index: 946

Text #9

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.4744. Min Act: -0.0000

Data Index: 616269 (C4 (Web Text))

Max Activating Token Index: 556

Text #10

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.4670. Min Act: -0.0000

Data Index: 1128215 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.4707. Min Act: -0.0000

Data Index: 909440 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.4674. Min Act: -0.0000

Data Index: 1182892 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.4788. Min Act: -0.0000

Data Index: 493365 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.4638. Min Act: -0.0000

Data Index: 611920 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.4590. Min Act: -0.0000

Data Index: 857996 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.4595. Min Act: -0.0000

Data Index: 1253631 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.4798. Min Act: -0.0000

Data Index: 5964 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.4306. Min Act: -0.0000

Data Index: 808209 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.4496. Min Act: -0.0000

Data Index: 740151 (C4 (Web Text))

Max Activating Token Index: 456