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

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

Neuron 1452 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1794. Min Range: -2.1794

Max Act: 2.1794. Min Act: -0.0000

Data Index: 383863 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 2.1794. Min Range: -2.1794

Max Act: 1.9683. Min Act: -0.0000

Data Index: 584691 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 2.1794. Min Range: -2.1794

Max Act: 1.9291. Min Act: -0.0000

Data Index: 455742 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 2.1794. Min Range: -2.1794

Max Act: 1.6645. Min Act: -0.0000

Data Index: 492221 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 2.1794. Min Range: -2.1794

Max Act: 1.9965. Min Act: -0.0000

Data Index: 100908 (C4 (Web Text))

Max Activating Token Index: 217

Text #5

Max Range: 2.1794. Min Range: -2.1794

Max Act: 1.8527. Min Act: -0.0000

Data Index: 307902 (C4 (Web Text))

Max Activating Token Index: 488

Text #6

Max Range: 2.1794. Min Range: -2.1794

Max Act: 1.6901. Min Act: -0.0000

Data Index: 461091 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 2.1794. Min Range: -2.1794

Max Act: 1.6059. Min Act: -0.0000

Data Index: 751460 (C4 (Web Text))

Max Activating Token Index: 811

Text #8

Max Range: 2.1794. Min Range: -2.1794

Max Act: 1.5901. Min Act: -0.0000

Data Index: 785066 (C4 (Web Text))

Max Activating Token Index: 248

Text #9

Max Range: 2.1794. Min Range: -2.1794

Max Act: 1.5876. Min Act: -0.0000

Data Index: 1292038 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 2.1794. Min Range: -2.1794

Max Act: 1.7421. Min Act: -0.0000

Data Index: 240839 (C4 (Web Text))

Max Activating Token Index: 522

Text #11

Max Range: 2.1794. Min Range: -2.1794

Max Act: 1.5922. Min Act: -0.0000

Data Index: 380394 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 2.1794. Min Range: -2.1794

Max Act: 1.6859. Min Act: -0.0000

Data Index: 194918 (C4 (Web Text))

Max Activating Token Index: 700

Text #13

Max Range: 2.1794. Min Range: -2.1794

Max Act: 1.7171. Min Act: -0.0000

Data Index: 649027 (C4 (Web Text))

Max Activating Token Index: 440

Text #14

Max Range: 2.1794. Min Range: -2.1794

Max Act: 1.4279. Min Act: -0.0000

Data Index: 1118226 (C4 (Web Text))

Max Activating Token Index: 708

Text #15

Max Range: 2.1794. Min Range: -2.1794

Max Act: 1.6793. Min Act: -0.0000

Data Index: 419919 (C4 (Web Text))

Max Activating Token Index: 377

Text #16

Max Range: 2.1794. Min Range: -2.1794

Max Act: 1.5790. Min Act: -0.0000

Data Index: 109360 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 2.1794. Min Range: -2.1794

Max Act: 1.3735. Min Act: -0.0000

Data Index: 823194 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 2.1794. Min Range: -2.1794

Max Act: 1.4868. Min Act: -0.0000

Data Index: 682429 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 2.1794. Min Range: -2.1794

Max Act: 1.4431. Min Act: -0.0000

Data Index: 1349686 (C4 (Web Text))

Max Activating Token Index: 721