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

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

Neuron 4782 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3978. Min Range: -5.3978

Max Act: 5.3978. Min Act: -0.0000

Data Index: 332689 (C4 (Web Text))

Max Activating Token Index: 258

Text #1

Max Range: 5.3978. Min Range: -5.3978

Max Act: 5.1433. Min Act: -0.0000

Data Index: 303235 (C4 (Web Text))

Max Activating Token Index: 756

Text #2

Max Range: 5.3978. Min Range: -5.3978

Max Act: 3.7442. Min Act: -0.0000

Data Index: 956141 (C4 (Web Text))

Max Activating Token Index: 445

Text #3

Max Range: 5.3978. Min Range: -5.3978

Max Act: 3.8563. Min Act: -0.0000

Data Index: 859339 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 5.3978. Min Range: -5.3978

Max Act: 4.0352. Min Act: -0.0000

Data Index: 1309267 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 5.3978. Min Range: -5.3978

Max Act: 3.4857. Min Act: -0.0000

Data Index: 496086 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 5.3978. Min Range: -5.3978

Max Act: 3.8016. Min Act: -0.0000

Data Index: 649261 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 5.3978. Min Range: -5.3978

Max Act: 3.2427. Min Act: -0.0000

Data Index: 325790 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 5.3978. Min Range: -5.3978

Max Act: 3.3357. Min Act: -0.0000

Data Index: 1033181 (C4 (Web Text))

Max Activating Token Index: 486

Text #9

Max Range: 5.3978. Min Range: -5.3978

Max Act: 2.9490. Min Act: -0.0000

Data Index: 411647 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 5.3978. Min Range: -5.3978

Max Act: 2.7337. Min Act: -0.0000

Data Index: 875769 (C4 (Web Text))

Max Activating Token Index: 1004

Text #11

Max Range: 5.3978. Min Range: -5.3978

Max Act: 2.8830. Min Act: -0.0000

Data Index: 519473 (C4 (Web Text))

Max Activating Token Index: 201

Text #12

Max Range: 5.3978. Min Range: -5.3978

Max Act: 2.6091. Min Act: -0.0000

Data Index: 688850 (C4 (Web Text))

Max Activating Token Index: 395

Text #13

Max Range: 5.3978. Min Range: -5.3978

Max Act: 2.6642. Min Act: -0.0000

Data Index: 725602 (C4 (Web Text))

Max Activating Token Index: 216

Text #14

Max Range: 5.3978. Min Range: -5.3978

Max Act: 2.1513. Min Act: -0.0000

Data Index: 57592 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 5.3978. Min Range: -5.3978

Max Act: 2.3821. Min Act: -0.0000

Data Index: 1303876 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 5.3978. Min Range: -5.3978

Max Act: 2.4878. Min Act: -0.0000

Data Index: 971203 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 5.3978. Min Range: -5.3978

Max Act: 2.2393. Min Act: -0.0000

Data Index: 887545 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 5.3978. Min Range: -5.3978

Max Act: 2.2822. Min Act: -0.0000

Data Index: 1272693 (C4 (Web Text))

Max Activating Token Index: 908

Text #19

Max Range: 5.3978. Min Range: -5.3978

Max Act: 2.1638. Min Act: -0.0000

Data Index: 408869 (C4 (Web Text))

Max Activating Token Index: 635