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

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

Neuron 3322 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: 0.3873. Min Range: -0.3873

Max Act: 0.3873. Min Act: -0.0000

Data Index: 585060 (C4 (Web Text))

Max Activating Token Index: 504

Text #1

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.2895. Min Act: -0.0000

Data Index: 235968 (C4 (Web Text))

Max Activating Token Index: 645

Text #2

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.2887. Min Act: 0.0000

Data Index: 495936 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.2995. Min Act: -0.0000

Data Index: 438319 (C4 (Web Text))

Max Activating Token Index: 704

Text #4

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.2676. Min Act: -0.0000

Data Index: 737237 (C4 (Web Text))

Max Activating Token Index: 545

Text #5

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.2632. Min Act: -0.0000

Data Index: 28904 (C4 (Web Text))

Max Activating Token Index: 626

Text #6

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.2482. Min Act: -0.0000

Data Index: 85100 (C4 (Web Text))

Max Activating Token Index: 506

Text #7

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.2738. Min Act: -0.0000

Data Index: 476437 (C4 (Web Text))

Max Activating Token Index: 554

Text #8

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.2506. Min Act: -0.0000

Data Index: 1105970 (C4 (Web Text))

Max Activating Token Index: 886

Text #9

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.2526. Min Act: -0.0000

Data Index: 542057 (C4 (Web Text))

Max Activating Token Index: 816

Text #10

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.2610. Min Act: -0.0000

Data Index: 440403 (C4 (Web Text))

Max Activating Token Index: 426

Text #11

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.2492. Min Act: -0.0000

Data Index: 413077 (C4 (Web Text))

Max Activating Token Index: 251

Text #12

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.2308. Min Act: -0.0000

Data Index: 546364 (C4 (Web Text))

Max Activating Token Index: 191

Text #13

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.2418. Min Act: -0.0000

Data Index: 216369 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.2446. Min Act: -0.0000

Data Index: 1029542 (C4 (Web Text))

Max Activating Token Index: 1002

Text #15

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.2486. Min Act: -0.0000

Data Index: 1040803 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.2406. Min Act: -0.0000

Data Index: 501408 (C4 (Web Text))

Max Activating Token Index: 198

Text #17

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.2086. Min Act: -0.0000

Data Index: 1193623 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.2389. Min Act: -0.0000

Data Index: 953328 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 0.3873. Min Range: -0.3873

Max Act: 0.2445. Min Act: -0.0000

Data Index: 891641 (C4 (Web Text))

Max Activating Token Index: 680