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

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

Neuron 3294 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1767. Min Range: -4.1767

Max Act: 3.7695. Min Act: -0.0000

Data Index: 157079 (C4 (Web Text))

Max Activating Token Index: 710

Text #1

Max Range: 4.1767. Min Range: -4.1767

Max Act: 3.8967. Min Act: -0.0001

Data Index: 175197 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 4.1767. Min Range: -4.1767

Max Act: 4.1767. Min Act: -0.0000

Data Index: 834872 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 4.1767. Min Range: -4.1767

Max Act: 3.6327. Min Act: -0.0000

Data Index: 239942 (C4 (Web Text))

Max Activating Token Index: 529

Text #4

Max Range: 4.1767. Min Range: -4.1767

Max Act: 3.7936. Min Act: -0.0001

Data Index: 101522 (C4 (Web Text))

Max Activating Token Index: 125

Text #5

Max Range: 4.1767. Min Range: -4.1767

Max Act: 3.7611. Min Act: -0.0000

Data Index: 290087 (C4 (Web Text))

Max Activating Token Index: 48

Text #6

Max Range: 4.1767. Min Range: -4.1767

Max Act: 3.4071. Min Act: -0.0001

Data Index: 21277 (C4 (Web Text))

Max Activating Token Index: 724

Text #7

Max Range: 4.1767. Min Range: -4.1767

Max Act: 3.6589. Min Act: -0.0000

Data Index: 325458 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 4.1767. Min Range: -4.1767

Max Act: 3.3420. Min Act: -0.0000

Data Index: 653754 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 4.1767. Min Range: -4.1767

Max Act: 3.7849. Min Act: -0.0000

Data Index: 335055 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 4.1767. Min Range: -4.1767

Max Act: 3.6297. Min Act: -0.0000

Data Index: 586728 (C4 (Web Text))

Max Activating Token Index: 602

Text #11

Max Range: 4.1767. Min Range: -4.1767

Max Act: 3.5829. Min Act: -0.0001

Data Index: 704453 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 4.1767. Min Range: -4.1767

Max Act: 3.5508. Min Act: -0.0000

Data Index: 998236 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 4.1767. Min Range: -4.1767

Max Act: 3.5363. Min Act: -0.0001

Data Index: 1325135 (C4 (Web Text))

Max Activating Token Index: 538

Text #14

Max Range: 4.1767. Min Range: -4.1767

Max Act: 3.0375. Min Act: -0.0000

Data Index: 278008 (C4 (Web Text))

Max Activating Token Index: 677

Text #15

Max Range: 4.1767. Min Range: -4.1767

Max Act: 3.6729. Min Act: -0.0000

Data Index: 183297 (C4 (Web Text))

Max Activating Token Index: 385

Text #16

Max Range: 4.1767. Min Range: -4.1767

Max Act: 3.3516. Min Act: -0.0000

Data Index: 677731 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 4.1767. Min Range: -4.1767

Max Act: 3.2098. Min Act: -0.0001

Data Index: 411743 (C4 (Web Text))

Max Activating Token Index: 304

Text #18

Max Range: 4.1767. Min Range: -4.1767

Max Act: 3.0486. Min Act: -0.0000

Data Index: 1049120 (C4 (Web Text))

Max Activating Token Index: 420

Text #19

Max Range: 4.1767. Min Range: -4.1767

Max Act: 3.4854. Min Act: -0.0001

Data Index: 750073 (C4 (Web Text))

Max Activating Token Index: 19