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

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

Neuron 1065 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.4802. Min Act: -0.0002

Data Index: 922860 (C4 (Web Text))

Max Activating Token Index: 510

Text #1

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.4570. Min Act: -0.0003

Data Index: 216563 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.4527. Min Act: -0.0002

Data Index: 739176 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.4211. Min Act: -0.0003

Data Index: 558425 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.4137. Min Act: -0.0002

Data Index: 527370 (C4 (Web Text))

Max Activating Token Index: 17

Text #5

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.4096. Min Act: -0.0003

Data Index: 1170307 (C4 (Web Text))

Max Activating Token Index: 391

Text #6

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.3955. Min Act: -0.0002

Data Index: 727524 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.3953. Min Act: -0.0002

Data Index: 887970 (C4 (Web Text))

Max Activating Token Index: 135

Text #8

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.3931. Min Act: -0.0003

Data Index: 1041837 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.3766. Min Act: -0.0002

Data Index: 395681 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.3588. Min Act: -0.0002

Data Index: 6688 (C4 (Web Text))

Max Activating Token Index: 568

Text #11

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.3609. Min Act: -0.0002

Data Index: 361219 (C4 (Web Text))

Max Activating Token Index: 433

Text #12

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.3722. Min Act: -0.0002

Data Index: 428503 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.3707. Min Act: -0.0002

Data Index: 158467 (C4 (Web Text))

Max Activating Token Index: 743

Text #14

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.3678. Min Act: -0.0003

Data Index: 194161 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.3670. Min Act: -0.0003

Data Index: 1333242 (C4 (Web Text))

Max Activating Token Index: 13

Text #16

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.3542. Min Act: -0.0002

Data Index: 307738 (C4 (Web Text))

Max Activating Token Index: 314

Text #17

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.3620. Min Act: -0.0002

Data Index: 1296491 (C4 (Web Text))

Max Activating Token Index: 734

Text #18

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.3499. Min Act: -0.0002

Data Index: 632931 (C4 (Web Text))

Max Activating Token Index: 468

Text #19

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.3590. Min Act: -0.0002

Data Index: 933394 (C4 (Web Text))

Max Activating Token Index: 132