Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1357 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.7019. Min Range: -2.7019

Max Act: 2.7019. Min Act: -0.0000

Data Index: 1497159 (Python Code)

Max Activating Token Index: 62

Text #1

Max Range: 2.7019. Min Range: -2.7019

Max Act: 2.3079. Min Act: -0.0000

Data Index: 1473752 (Python Code)

Max Activating Token Index: 321

Text #2

Max Range: 2.7019. Min Range: -2.7019

Max Act: 2.4768. Min Act: -0.0000

Data Index: 1443265 (Python Code)

Max Activating Token Index: 664

Text #3

Max Range: 2.7019. Min Range: -2.7019

Max Act: 2.4605. Min Act: -0.0000

Data Index: 1417409 (Python Code)

Max Activating Token Index: 532

Text #4

Max Range: 2.7019. Min Range: -2.7019

Max Act: 2.3415. Min Act: -0.0000

Data Index: 1578584 (Python Code)

Max Activating Token Index: 874

Text #5

Max Range: 2.7019. Min Range: -2.7019

Max Act: 2.3192. Min Act: -0.0000

Data Index: 1565717 (Python Code)

Max Activating Token Index: 276

Text #6

Max Range: 2.7019. Min Range: -2.7019

Max Act: 1.9179. Min Act: -0.0000

Data Index: 1371087 (Python Code)

Max Activating Token Index: 898

Text #7

Max Range: 2.7019. Min Range: -2.7019

Max Act: 2.0928. Min Act: -0.0000

Data Index: 1552053 (Python Code)

Max Activating Token Index: 29

Text #8

Max Range: 2.7019. Min Range: -2.7019

Max Act: 1.8918. Min Act: -0.0000

Data Index: 1602380 (Python Code)

Max Activating Token Index: 673

Text #9

Max Range: 2.7019. Min Range: -2.7019

Max Act: 1.7570. Min Act: -0.0000

Data Index: 113523 (C4 (Web Text))

Max Activating Token Index: 978

Text #10

Max Range: 2.7019. Min Range: -2.7019

Max Act: 1.7678. Min Act: -0.0000

Data Index: 1418224 (Python Code)

Max Activating Token Index: 788

Text #11

Max Range: 2.7019. Min Range: -2.7019

Max Act: 1.9391. Min Act: -0.0000

Data Index: 1400591 (Python Code)

Max Activating Token Index: 357

Text #12

Max Range: 2.7019. Min Range: -2.7019

Max Act: 1.8216. Min Act: -0.0000

Data Index: 1458631 (Python Code)

Max Activating Token Index: 616

Text #13

Max Range: 2.7019. Min Range: -2.7019

Max Act: 1.7810. Min Act: -0.0000

Data Index: 1586668 (Python Code)

Max Activating Token Index: 118

Text #14

Max Range: 2.7019. Min Range: -2.7019

Max Act: 1.9059. Min Act: -0.0000

Data Index: 239513 (C4 (Web Text))

Max Activating Token Index: 961

Text #15

Max Range: 2.7019. Min Range: -2.7019

Max Act: 1.8850. Min Act: 0.0000

Data Index: 1552823 (Python Code)

Max Activating Token Index: 891

Text #16

Max Range: 2.7019. Min Range: -2.7019

Max Act: 1.8837. Min Act: -0.0000

Data Index: 1410447 (Python Code)

Max Activating Token Index: 74

Text #17

Max Range: 2.7019. Min Range: -2.7019

Max Act: 1.6710. Min Act: -0.0000

Data Index: 1560841 (Python Code)

Max Activating Token Index: 39

Text #18

Max Range: 2.7019. Min Range: -2.7019

Max Act: 1.6662. Min Act: -0.0000

Data Index: 1580256 (Python Code)

Max Activating Token Index: 422

Text #19

Max Range: 2.7019. Min Range: -2.7019

Max Act: 1.6291. Min Act: 0.0000

Data Index: 1532367 (Python Code)

Max Activating Token Index: 658