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

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

Neuron 784 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3725. Min Range: -0.3725

Max Act: 0.3725. Min Act: -0.0000

Data Index: 482080 (C4 (Web Text))

Max Activating Token Index: 458

Text #1

Max Range: 0.3725. Min Range: -0.3725

Max Act: 0.3255. Min Act: -0.0000

Data Index: 1072626 (C4 (Web Text))

Max Activating Token Index: 537

Text #2

Max Range: 0.3725. Min Range: -0.3725

Max Act: 0.3081. Min Act: -0.0000

Data Index: 739458 (C4 (Web Text))

Max Activating Token Index: 642

Text #3

Max Range: 0.3725. Min Range: -0.3725

Max Act: 0.3144. Min Act: -0.0000

Data Index: 549377 (C4 (Web Text))

Max Activating Token Index: 83

Text #4

Max Range: 0.3725. Min Range: -0.3725

Max Act: 0.2456. Min Act: -0.0000

Data Index: 1378223 (Python Code)

Max Activating Token Index: 822

Text #5

Max Range: 0.3725. Min Range: -0.3725

Max Act: 0.3017. Min Act: -0.0000

Data Index: 1281657 (C4 (Web Text))

Max Activating Token Index: 440

Text #6

Max Range: 0.3725. Min Range: -0.3725

Max Act: 0.3059. Min Act: -0.0000

Data Index: 218304 (C4 (Web Text))

Max Activating Token Index: 317

Text #7

Max Range: 0.3725. Min Range: -0.3725

Max Act: 0.2662. Min Act: -0.0000

Data Index: 628711 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 0.3725. Min Range: -0.3725

Max Act: 0.2635. Min Act: -0.0000

Data Index: 836281 (C4 (Web Text))

Max Activating Token Index: 423

Text #9

Max Range: 0.3725. Min Range: -0.3725

Max Act: 0.2696. Min Act: -0.0000

Data Index: 1114752 (C4 (Web Text))

Max Activating Token Index: 642

Text #10

Max Range: 0.3725. Min Range: -0.3725

Max Act: 0.2542. Min Act: -0.0000

Data Index: 103495 (C4 (Web Text))

Max Activating Token Index: 636

Text #11

Max Range: 0.3725. Min Range: -0.3725

Max Act: 0.2644. Min Act: -0.0000

Data Index: 558025 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 0.3725. Min Range: -0.3725

Max Act: 0.2480. Min Act: -0.0000

Data Index: 791000 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 0.3725. Min Range: -0.3725

Max Act: 0.2608. Min Act: -0.0000

Data Index: 106296 (C4 (Web Text))

Max Activating Token Index: 779

Text #14

Max Range: 0.3725. Min Range: -0.3725

Max Act: 0.2686. Min Act: -0.0000

Data Index: 347980 (C4 (Web Text))

Max Activating Token Index: 520

Text #15

Max Range: 0.3725. Min Range: -0.3725

Max Act: 0.2655. Min Act: -0.0000

Data Index: 777859 (C4 (Web Text))

Max Activating Token Index: 800

Text #16

Max Range: 0.3725. Min Range: -0.3725

Max Act: 0.2447. Min Act: -0.0000

Data Index: 574701 (C4 (Web Text))

Max Activating Token Index: 757

Text #17

Max Range: 0.3725. Min Range: -0.3725

Max Act: 0.2369. Min Act: -0.0000

Data Index: 771447 (C4 (Web Text))

Max Activating Token Index: 623

Text #18

Max Range: 0.3725. Min Range: -0.3725

Max Act: 0.2436. Min Act: -0.0000

Data Index: 34302 (C4 (Web Text))

Max Activating Token Index: 335

Text #19

Max Range: 0.3725. Min Range: -0.3725

Max Act: 0.2674. Min Act: -0.0000

Data Index: 1315313 (C4 (Web Text))

Max Activating Token Index: 995