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

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

Neuron 2155 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: 0.8587. Min Range: -0.8587

Max Act: 0.8587. Min Act: -0.0000

Data Index: 1202579 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 0.8587. Min Range: -0.8587

Max Act: 0.7493. Min Act: -0.0000

Data Index: 1359236 (C4 (Web Text))

Max Activating Token Index: 363

Text #2

Max Range: 0.8587. Min Range: -0.8587

Max Act: 0.6384. Min Act: -0.0000

Data Index: 356118 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 0.8587. Min Range: -0.8587

Max Act: 0.6760. Min Act: -0.0000

Data Index: 498184 (C4 (Web Text))

Max Activating Token Index: 1012

Text #4

Max Range: 0.8587. Min Range: -0.8587

Max Act: 0.6295. Min Act: -0.0000

Data Index: 1151227 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 0.8587. Min Range: -0.8587

Max Act: 0.6438. Min Act: -0.0000

Data Index: 759316 (C4 (Web Text))

Max Activating Token Index: 101

Text #6

Max Range: 0.8587. Min Range: -0.8587

Max Act: 0.6190. Min Act: -0.0000

Data Index: 1227470 (C4 (Web Text))

Max Activating Token Index: 1004

Text #7

Max Range: 0.8587. Min Range: -0.8587

Max Act: 0.5702. Min Act: -0.0000

Data Index: 685527 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 0.8587. Min Range: -0.8587

Max Act: 0.5606. Min Act: -0.0000

Data Index: 81723 (C4 (Web Text))

Max Activating Token Index: 672

Text #9

Max Range: 0.8587. Min Range: -0.8587

Max Act: 0.5740. Min Act: -0.0000

Data Index: 315912 (C4 (Web Text))

Max Activating Token Index: 807

Text #10

Max Range: 0.8587. Min Range: -0.8587

Max Act: 0.5701. Min Act: -0.0000

Data Index: 364984 (C4 (Web Text))

Max Activating Token Index: 420

Text #11

Max Range: 0.8587. Min Range: -0.8587

Max Act: 0.5878. Min Act: -0.0000

Data Index: 244551 (C4 (Web Text))

Max Activating Token Index: 497

Text #12

Max Range: 0.8587. Min Range: -0.8587

Max Act: 0.5519. Min Act: -0.0000

Data Index: 171768 (C4 (Web Text))

Max Activating Token Index: 997

Text #13

Max Range: 0.8587. Min Range: -0.8587

Max Act: 0.5631. Min Act: -0.0000

Data Index: 161718 (C4 (Web Text))

Max Activating Token Index: 194

Text #14

Max Range: 0.8587. Min Range: -0.8587

Max Act: 0.5800. Min Act: -0.0000

Data Index: 164839 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 0.8587. Min Range: -0.8587

Max Act: 0.5817. Min Act: -0.0000

Data Index: 397141 (C4 (Web Text))

Max Activating Token Index: 739

Text #16

Max Range: 0.8587. Min Range: -0.8587

Max Act: 0.5698. Min Act: -0.0000

Data Index: 122735 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 0.8587. Min Range: -0.8587

Max Act: 0.5360. Min Act: -0.0000

Data Index: 661127 (C4 (Web Text))

Max Activating Token Index: 1007

Text #18

Max Range: 0.8587. Min Range: -0.8587

Max Act: 0.5754. Min Act: -0.0000

Data Index: 894233 (C4 (Web Text))

Max Activating Token Index: 381

Text #19

Max Range: 0.8587. Min Range: -0.8587

Max Act: 0.5667. Min Act: -0.0000

Data Index: 740815 (C4 (Web Text))

Max Activating Token Index: 161