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

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

Neuron 4323 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: 0.7502. Min Range: -0.7502

Max Act: 0.7317. Min Act: -0.0000

Data Index: 177891 (C4 (Web Text))

Max Activating Token Index: 475

Text #1

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.7502. Min Act: -0.0000

Data Index: 1343752 (C4 (Web Text))

Max Activating Token Index: 714

Text #2

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.7147. Min Act: -0.0000

Data Index: 1111505 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.7084. Min Act: -0.0000

Data Index: 725346 (C4 (Web Text))

Max Activating Token Index: 912

Text #4

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.6394. Min Act: -0.0000

Data Index: 423324 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.6296. Min Act: -0.0000

Data Index: 840931 (C4 (Web Text))

Max Activating Token Index: 868

Text #6

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.6279. Min Act: -0.0000

Data Index: 347484 (C4 (Web Text))

Max Activating Token Index: 381

Text #7

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.6062. Min Act: -0.0000

Data Index: 62049 (C4 (Web Text))

Max Activating Token Index: 269

Text #8

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.5539. Min Act: -0.0000

Data Index: 658765 (C4 (Web Text))

Max Activating Token Index: 657

Text #9

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.5867. Min Act: -0.0000

Data Index: 860584 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.5808. Min Act: -0.0000

Data Index: 1155631 (C4 (Web Text))

Max Activating Token Index: 840

Text #11

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.5810. Min Act: -0.0000

Data Index: 625047 (C4 (Web Text))

Max Activating Token Index: 189

Text #12

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.5803. Min Act: 0.0000

Data Index: 1319264 (C4 (Web Text))

Max Activating Token Index: 710

Text #13

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.5628. Min Act: -0.0000

Data Index: 1201020 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.5545. Min Act: -0.0000

Data Index: 49033 (C4 (Web Text))

Max Activating Token Index: 1022

Text #15

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.5439. Min Act: -0.0000

Data Index: 1137803 (C4 (Web Text))

Max Activating Token Index: 935

Text #16

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.5429. Min Act: -0.0000

Data Index: 249392 (C4 (Web Text))

Max Activating Token Index: 491

Text #17

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.5247. Min Act: -0.0000

Data Index: 440154 (C4 (Web Text))

Max Activating Token Index: 883

Text #18

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.5203. Min Act: -0.0000

Data Index: 667646 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.5178. Min Act: -0.0000

Data Index: 513529 (C4 (Web Text))

Max Activating Token Index: 381