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

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

Neuron 1960 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0544. Min Act: -0.0001

Data Index: 925616 (C4 (Web Text))

Max Activating Token Index: 570

Text #1

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0434. Min Act: -0.0001

Data Index: 38762 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0440. Min Act: -0.0001

Data Index: 1339549 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0453. Min Act: -0.0001

Data Index: 868029 (C4 (Web Text))

Max Activating Token Index: 387

Text #4

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0456. Min Act: -0.0001

Data Index: 499648 (C4 (Web Text))

Max Activating Token Index: 996

Text #5

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0413. Min Act: -0.0001

Data Index: 111609 (C4 (Web Text))

Max Activating Token Index: 794

Text #6

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0412. Min Act: -0.0001

Data Index: 430334 (C4 (Web Text))

Max Activating Token Index: 882

Text #7

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0426. Min Act: -0.0001

Data Index: 1113017 (C4 (Web Text))

Max Activating Token Index: 513

Text #8

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0401. Min Act: -0.0001

Data Index: 133668 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0418. Min Act: -0.0001

Data Index: 33939 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0430. Min Act: -0.0001

Data Index: 168478 (C4 (Web Text))

Max Activating Token Index: 513

Text #11

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0399. Min Act: -0.0001

Data Index: 325318 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0393. Min Act: -0.0001

Data Index: 832601 (C4 (Web Text))

Max Activating Token Index: 2

Text #13

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0399. Min Act: -0.0001

Data Index: 454613 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0406. Min Act: -0.0001

Data Index: 398792 (C4 (Web Text))

Max Activating Token Index: 270

Text #15

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0403. Min Act: -0.0001

Data Index: 779987 (C4 (Web Text))

Max Activating Token Index: 541

Text #16

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0408. Min Act: -0.0001

Data Index: 35277 (C4 (Web Text))

Max Activating Token Index: 155

Text #17

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0411. Min Act: -0.0001

Data Index: 912211 (C4 (Web Text))

Max Activating Token Index: 542

Text #18

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0385. Min Act: -0.0001

Data Index: 502626 (C4 (Web Text))

Max Activating Token Index: 107

Text #19

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0376. Min Act: -0.0001

Data Index: 1342605 (C4 (Web Text))

Max Activating Token Index: 44