Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1477 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0816. Min Act: -0.0002

Data Index: 1285719 (C4 (Web Text))

Max Activating Token Index: 386

Text #1

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0738. Min Act: -0.0002

Data Index: 547364 (C4 (Web Text))

Max Activating Token Index: 815

Text #2

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0723. Min Act: -0.0002

Data Index: 539469 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0700. Min Act: -0.0002

Data Index: 723722 (C4 (Web Text))

Max Activating Token Index: 485

Text #4

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0705. Min Act: -0.0002

Data Index: 1253876 (C4 (Web Text))

Max Activating Token Index: 783

Text #5

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0674. Min Act: -0.0002

Data Index: 571304 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0574. Min Act: -0.0002

Data Index: 638248 (C4 (Web Text))

Max Activating Token Index: 309

Text #7

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0631. Min Act: -0.0002

Data Index: 1034918 (C4 (Web Text))

Max Activating Token Index: 966

Text #8

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0609. Min Act: -0.0002

Data Index: 756213 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0641. Min Act: -0.0002

Data Index: 769540 (C4 (Web Text))

Max Activating Token Index: 150

Text #10

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0601. Min Act: -0.0002

Data Index: 1287531 (C4 (Web Text))

Max Activating Token Index: 478

Text #11

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0629. Min Act: -0.0002

Data Index: 762859 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0597. Min Act: -0.0002

Data Index: 223885 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0588. Min Act: -0.0002

Data Index: 769612 (C4 (Web Text))

Max Activating Token Index: 781

Text #14

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0603. Min Act: -0.0002

Data Index: 872456 (C4 (Web Text))

Max Activating Token Index: 496

Text #15

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0616. Min Act: -0.0002

Data Index: 316951 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0585. Min Act: -0.0002

Data Index: 620635 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0583. Min Act: -0.0002

Data Index: 1319542 (C4 (Web Text))

Max Activating Token Index: 476

Text #18

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0582. Min Act: -0.0002

Data Index: 733135 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0546. Min Act: -0.0002

Data Index: 466435 (C4 (Web Text))

Max Activating Token Index: 267