Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 734 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.3333. Min Act: -0.0000

Data Index: 652052 (C4 (Web Text))

Max Activating Token Index: 483

Text #1

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2862. Min Act: -0.0000

Data Index: 912442 (C4 (Web Text))

Max Activating Token Index: 468

Text #2

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.3025. Min Act: -0.0000

Data Index: 1012903 (C4 (Web Text))

Max Activating Token Index: 336

Text #3

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2968. Min Act: -0.0000

Data Index: 618713 (C4 (Web Text))

Max Activating Token Index: 283

Text #4

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2707. Min Act: -0.0000

Data Index: 973968 (C4 (Web Text))

Max Activating Token Index: 1010

Text #5

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2808. Min Act: -0.0000

Data Index: 1432357 (Python Code)

Max Activating Token Index: 932

Text #6

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2763. Min Act: -0.0000

Data Index: 465239 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2785. Min Act: -0.0000

Data Index: 1084247 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2589. Min Act: -0.0000

Data Index: 222302 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2818. Min Act: -0.0000

Data Index: 263668 (C4 (Web Text))

Max Activating Token Index: 799

Text #10

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2598. Min Act: -0.0000

Data Index: 739458 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2730. Min Act: -0.0000

Data Index: 335962 (C4 (Web Text))

Max Activating Token Index: 739

Text #12

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2811. Min Act: -0.0000

Data Index: 404510 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2591. Min Act: -0.0000

Data Index: 22791 (C4 (Web Text))

Max Activating Token Index: 1016

Text #14

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2690. Min Act: -0.0000

Data Index: 893815 (C4 (Web Text))

Max Activating Token Index: 790

Text #15

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2457. Min Act: -0.0000

Data Index: 1327199 (C4 (Web Text))

Max Activating Token Index: 768

Text #16

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2466. Min Act: -0.0000

Data Index: 766381 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2512. Min Act: -0.0000

Data Index: 926867 (C4 (Web Text))

Max Activating Token Index: 99

Text #18

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2336. Min Act: -0.0000

Data Index: 1358302 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2607. Min Act: -0.0000

Data Index: 1183581 (C4 (Web Text))

Max Activating Token Index: 140