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

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

Neuron 3633 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.9430. Min Act: -0.0000

Data Index: 341104 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.8782. Min Act: -0.0000

Data Index: 943808 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.8605. Min Act: -0.0000

Data Index: 1278578 (C4 (Web Text))

Max Activating Token Index: 241

Text #3

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.8121. Min Act: -0.0000

Data Index: 168211 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.7909. Min Act: -0.0000

Data Index: 530238 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.8324. Min Act: -0.0000

Data Index: 365437 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.7510. Min Act: -0.0000

Data Index: 748201 (C4 (Web Text))

Max Activating Token Index: 877

Text #7

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.7502. Min Act: -0.0000

Data Index: 119668 (C4 (Web Text))

Max Activating Token Index: 442

Text #8

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.7207. Min Act: -0.0000

Data Index: 1089887 (C4 (Web Text))

Max Activating Token Index: 749

Text #9

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.7145. Min Act: -0.0000

Data Index: 1274689 (C4 (Web Text))

Max Activating Token Index: 919

Text #10

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.7100. Min Act: -0.0000

Data Index: 179360 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.7280. Min Act: -0.0000

Data Index: 603197 (C4 (Web Text))

Max Activating Token Index: 559

Text #12

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.7265. Min Act: -0.0000

Data Index: 786411 (C4 (Web Text))

Max Activating Token Index: 360

Text #13

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.7332. Min Act: -0.0000

Data Index: 523786 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.7297. Min Act: -0.0000

Data Index: 1290654 (C4 (Web Text))

Max Activating Token Index: 914

Text #15

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.6791. Min Act: -0.0000

Data Index: 154665 (C4 (Web Text))

Max Activating Token Index: 463

Text #16

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.6941. Min Act: -0.0000

Data Index: 786622 (C4 (Web Text))

Max Activating Token Index: 849

Text #17

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.7334. Min Act: -0.0000

Data Index: 478737 (C4 (Web Text))

Max Activating Token Index: 793

Text #18

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.6896. Min Act: -0.0000

Data Index: 547081 (C4 (Web Text))

Max Activating Token Index: 722

Text #19

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.6841. Min Act: -0.0000

Data Index: 309619 (C4 (Web Text))

Max Activating Token Index: 541