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

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

Neuron 3001 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0954. Min Act: -0.0002

Data Index: 1027222 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0817. Min Act: -0.0002

Data Index: 467585 (C4 (Web Text))

Max Activating Token Index: 698

Text #2

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0719. Min Act: -0.0002

Data Index: 1027877 (C4 (Web Text))

Max Activating Token Index: 490

Text #3

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0709. Min Act: -0.0002

Data Index: 587467 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0721. Min Act: -0.0002

Data Index: 848951 (C4 (Web Text))

Max Activating Token Index: 507

Text #5

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0728. Min Act: -0.0002

Data Index: 865243 (C4 (Web Text))

Max Activating Token Index: 342

Text #6

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0672. Min Act: -0.0002

Data Index: 528862 (C4 (Web Text))

Max Activating Token Index: 438

Text #7

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0704. Min Act: -0.0002

Data Index: 1080110 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0659. Min Act: -0.0002

Data Index: 495820 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0674. Min Act: -0.0002

Data Index: 356937 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0623. Min Act: -0.0002

Data Index: 350561 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0658. Min Act: -0.0002

Data Index: 1159382 (C4 (Web Text))

Max Activating Token Index: 294

Text #12

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0624. Min Act: -0.0002

Data Index: 919409 (C4 (Web Text))

Max Activating Token Index: 387

Text #13

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0582. Min Act: -0.0002

Data Index: 164952 (C4 (Web Text))

Max Activating Token Index: 496

Text #14

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0597. Min Act: -0.0002

Data Index: 276606 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0576. Min Act: -0.0002

Data Index: 1200409 (C4 (Web Text))

Max Activating Token Index: 773

Text #16

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0569. Min Act: -0.0002

Data Index: 721782 (C4 (Web Text))

Max Activating Token Index: 574

Text #17

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0569. Min Act: -0.0002

Data Index: 1223471 (C4 (Web Text))

Max Activating Token Index: 739

Text #18

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0540. Min Act: -0.0002

Data Index: 837889 (C4 (Web Text))

Max Activating Token Index: 451

Text #19

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0543. Min Act: -0.0002

Data Index: 1042862 (C4 (Web Text))

Max Activating Token Index: 944