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

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

Neuron 3073 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.6244. Min Act: -0.0001

Data Index: 586295 (C4 (Web Text))

Max Activating Token Index: 378

Text #1

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.6207. Min Act: -0.0001

Data Index: 337941 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.5814. Min Act: -0.0001

Data Index: 717264 (C4 (Web Text))

Max Activating Token Index: 1009

Text #3

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.5783. Min Act: -0.0001

Data Index: 215769 (C4 (Web Text))

Max Activating Token Index: 453

Text #4

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.5736. Min Act: -0.0001

Data Index: 1075512 (C4 (Web Text))

Max Activating Token Index: 687

Text #5

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.5722. Min Act: -0.0001

Data Index: 4905 (C4 (Web Text))

Max Activating Token Index: 410

Text #6

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.5718. Min Act: -0.0001

Data Index: 22931 (C4 (Web Text))

Max Activating Token Index: 836

Text #7

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.5498. Min Act: -0.0001

Data Index: 743012 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.5575. Min Act: -0.0001

Data Index: 18888 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.5261. Min Act: -0.0001

Data Index: 1241101 (C4 (Web Text))

Max Activating Token Index: 718

Text #10

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.5563. Min Act: -0.0001

Data Index: 54021 (C4 (Web Text))

Max Activating Token Index: 244

Text #11

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.5359. Min Act: -0.0001

Data Index: 1345267 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.5353. Min Act: -0.0001

Data Index: 149675 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.5455. Min Act: -0.0001

Data Index: 465660 (C4 (Web Text))

Max Activating Token Index: 211

Text #14

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.4622. Min Act: -0.0000

Data Index: 767892 (C4 (Web Text))

Max Activating Token Index: 700

Text #15

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.5462. Min Act: -0.0001

Data Index: 528837 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.5253. Min Act: -0.0001

Data Index: 1219582 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.4875. Min Act: -0.0001

Data Index: 522006 (C4 (Web Text))

Max Activating Token Index: 616

Text #18

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.5345. Min Act: -0.0001

Data Index: 1227170 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.5493. Min Act: -0.0001

Data Index: 330934 (C4 (Web Text))

Max Activating Token Index: 78