Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1058 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 5.0844. Min Range: -5.0844

Max Act: 5.0844. Min Act: -0.0001

Data Index: 603313 (C4 (Web Text))

Max Activating Token Index: 427

Text #1

Max Range: 5.0844. Min Range: -5.0844

Max Act: 4.6537. Min Act: -0.0001

Data Index: 963753 (C4 (Web Text))

Max Activating Token Index: 636

Text #2

Max Range: 5.0844. Min Range: -5.0844

Max Act: 4.1710. Min Act: -0.0001

Data Index: 255734 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 5.0844. Min Range: -5.0844

Max Act: 4.1730. Min Act: -0.0001

Data Index: 479889 (C4 (Web Text))

Max Activating Token Index: 698

Text #4

Max Range: 5.0844. Min Range: -5.0844

Max Act: 4.1593. Min Act: -0.0001

Data Index: 96848 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 5.0844. Min Range: -5.0844

Max Act: 4.1478. Min Act: -0.0001

Data Index: 1038344 (C4 (Web Text))

Max Activating Token Index: 480

Text #6

Max Range: 5.0844. Min Range: -5.0844

Max Act: 4.1432. Min Act: -0.0001

Data Index: 374171 (C4 (Web Text))

Max Activating Token Index: 503

Text #7

Max Range: 5.0844. Min Range: -5.0844

Max Act: 3.7056. Min Act: -0.0001

Data Index: 485723 (C4 (Web Text))

Max Activating Token Index: 307

Text #8

Max Range: 5.0844. Min Range: -5.0844

Max Act: 3.8698. Min Act: -0.0001

Data Index: 1120201 (C4 (Web Text))

Max Activating Token Index: 357

Text #9

Max Range: 5.0844. Min Range: -5.0844

Max Act: 3.9563. Min Act: -0.0001

Data Index: 635967 (C4 (Web Text))

Max Activating Token Index: 626

Text #10

Max Range: 5.0844. Min Range: -5.0844

Max Act: 4.1120. Min Act: -0.0001

Data Index: 682082 (C4 (Web Text))

Max Activating Token Index: 404

Text #11

Max Range: 5.0844. Min Range: -5.0844

Max Act: 3.9319. Min Act: -0.0001

Data Index: 320781 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 5.0844. Min Range: -5.0844

Max Act: 3.6747. Min Act: -0.0001

Data Index: 579882 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 5.0844. Min Range: -5.0844

Max Act: 3.8142. Min Act: -0.0001

Data Index: 282823 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 5.0844. Min Range: -5.0844

Max Act: 3.6632. Min Act: -0.0001

Data Index: 252666 (C4 (Web Text))

Max Activating Token Index: 667

Text #15

Max Range: 5.0844. Min Range: -5.0844

Max Act: 4.0722. Min Act: -0.0001

Data Index: 310501 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 5.0844. Min Range: -5.0844

Max Act: 3.5735. Min Act: -0.0001

Data Index: 1062217 (C4 (Web Text))

Max Activating Token Index: 1021

Text #17

Max Range: 5.0844. Min Range: -5.0844

Max Act: 3.7329. Min Act: -0.0001

Data Index: 1285859 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 5.0844. Min Range: -5.0844

Max Act: 3.7000. Min Act: -0.0001

Data Index: 442294 (C4 (Web Text))

Max Activating Token Index: 757

Text #19

Max Range: 5.0844. Min Range: -5.0844

Max Act: 3.6994. Min Act: -0.0001

Data Index: 179301 (C4 (Web Text))

Max Activating Token Index: 753