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

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

Neuron 3043 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: 6.0628. Min Range: -6.0628

Max Act: 6.0628. Min Act: -0.0000

Data Index: 866648 (C4 (Web Text))

Max Activating Token Index: 577

Text #1

Max Range: 6.0628. Min Range: -6.0628

Max Act: 5.8998. Min Act: -0.0000

Data Index: 763742 (C4 (Web Text))

Max Activating Token Index: 798

Text #2

Max Range: 6.0628. Min Range: -6.0628

Max Act: 5.3401. Min Act: -0.0000

Data Index: 1049400 (C4 (Web Text))

Max Activating Token Index: 559

Text #3

Max Range: 6.0628. Min Range: -6.0628

Max Act: 4.9374. Min Act: -0.0000

Data Index: 455784 (C4 (Web Text))

Max Activating Token Index: 886

Text #4

Max Range: 6.0628. Min Range: -6.0628

Max Act: 4.7886. Min Act: -0.0000

Data Index: 403998 (C4 (Web Text))

Max Activating Token Index: 367

Text #5

Max Range: 6.0628. Min Range: -6.0628

Max Act: 4.9417. Min Act: -0.0000

Data Index: 552491 (C4 (Web Text))

Max Activating Token Index: 463

Text #6

Max Range: 6.0628. Min Range: -6.0628

Max Act: 4.6645. Min Act: -0.0000

Data Index: 1216950 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 6.0628. Min Range: -6.0628

Max Act: 3.9458. Min Act: -0.0000

Data Index: 39350 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 6.0628. Min Range: -6.0628

Max Act: 2.4885. Min Act: -0.0000

Data Index: 306739 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 6.0628. Min Range: -6.0628

Max Act: 1.9295. Min Act: -0.0000

Data Index: 414827 (C4 (Web Text))

Max Activating Token Index: 404

Text #10

Max Range: 6.0628. Min Range: -6.0628

Max Act: 1.5708. Min Act: -0.0000

Data Index: 1217340 (C4 (Web Text))

Max Activating Token Index: 766

Text #11

Max Range: 6.0628. Min Range: -6.0628

Max Act: 2.0480. Min Act: 0.0000

Data Index: 80374 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 6.0628. Min Range: -6.0628

Max Act: 1.9604. Min Act: -0.0000

Data Index: 90112 (C4 (Web Text))

Max Activating Token Index: 240

Text #13

Max Range: 6.0628. Min Range: -6.0628

Max Act: 1.9759. Min Act: -0.0000

Data Index: 234131 (C4 (Web Text))

Max Activating Token Index: 518

Text #14

Max Range: 6.0628. Min Range: -6.0628

Max Act: 1.6029. Min Act: -0.0000

Data Index: 251393 (C4 (Web Text))

Max Activating Token Index: 786

Text #15

Max Range: 6.0628. Min Range: -6.0628

Max Act: 1.6248. Min Act: -0.0000

Data Index: 139241 (C4 (Web Text))

Max Activating Token Index: 202

Text #16

Max Range: 6.0628. Min Range: -6.0628

Max Act: 1.5484. Min Act: -0.0000

Data Index: 657793 (C4 (Web Text))

Max Activating Token Index: 338

Text #17

Max Range: 6.0628. Min Range: -6.0628

Max Act: 1.6489. Min Act: -0.0000

Data Index: 890076 (C4 (Web Text))

Max Activating Token Index: 438

Text #18

Max Range: 6.0628. Min Range: -6.0628

Max Act: 1.5760. Min Act: -0.0000

Data Index: 479032 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 6.0628. Min Range: -6.0628

Max Act: 1.6343. Min Act: -0.0000

Data Index: 1238083 (C4 (Web Text))

Max Activating Token Index: 330