Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 643 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.4205. Min Act: -0.0001

Data Index: 743422 (C4 (Web Text))

Max Activating Token Index: 834

Text #1

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.4266. Min Act: -0.0001

Data Index: 1159250 (C4 (Web Text))

Max Activating Token Index: 819

Text #2

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.3892. Min Act: -0.0001

Data Index: 108326 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.3768. Min Act: -0.0001

Data Index: 428890 (C4 (Web Text))

Max Activating Token Index: 667

Text #4

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.3449. Min Act: -0.0001

Data Index: 792087 (C4 (Web Text))

Max Activating Token Index: 700

Text #5

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.3659. Min Act: -0.0001

Data Index: 940392 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.3625. Min Act: -0.0001

Data Index: 180243 (C4 (Web Text))

Max Activating Token Index: 680

Text #7

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.3611. Min Act: -0.0001

Data Index: 1322191 (C4 (Web Text))

Max Activating Token Index: 452

Text #8

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.3594. Min Act: -0.0001

Data Index: 1300657 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.3798. Min Act: -0.0001

Data Index: 1130417 (C4 (Web Text))

Max Activating Token Index: 514

Text #10

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.3596. Min Act: -0.0001

Data Index: 1160241 (C4 (Web Text))

Max Activating Token Index: 250

Text #11

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.3604. Min Act: -0.0001

Data Index: 502361 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.3585. Min Act: -0.0001

Data Index: 137571 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.3493. Min Act: -0.0001

Data Index: 12724 (C4 (Web Text))

Max Activating Token Index: 855

Text #14

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.3442. Min Act: -0.0001

Data Index: 623901 (C4 (Web Text))

Max Activating Token Index: 599

Text #15

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.3582. Min Act: -0.0001

Data Index: 290733 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.3627. Min Act: -0.0001

Data Index: 413154 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.3372. Min Act: -0.0001

Data Index: 935397 (C4 (Web Text))

Max Activating Token Index: 607

Text #18

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.3346. Min Act: -0.0001

Data Index: 1161910 (C4 (Web Text))

Max Activating Token Index: 587

Text #19

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.3562. Min Act: -0.0001

Data Index: 728735 (C4 (Web Text))

Max Activating Token Index: 956