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

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

Neuron 5812 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 10.8638. Min Range: -10.8638

Max Act: 10.8638. Min Act: -0.0000

Data Index: 718013 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 10.8638. Min Range: -10.8638

Max Act: 2.9295. Min Act: -0.0000

Data Index: 1638559 (Python Code)

Max Activating Token Index: 60

Text #2

Max Range: 10.8638. Min Range: -10.8638

Max Act: 1.3519. Min Act: -0.0000

Data Index: 484423 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 10.8638. Min Range: -10.8638

Max Act: 0.4626. Min Act: -0.0000

Data Index: 1426781 (Python Code)

Max Activating Token Index: 920

Text #4

Max Range: 10.8638. Min Range: -10.8638

Max Act: 0.0787. Min Act: -0.0000

Data Index: 829301 (C4 (Web Text))

Max Activating Token Index: 64

Text #5

Max Range: 10.8638. Min Range: -10.8638

Max Act: 0.0665. Min Act: -0.0000

Data Index: 403981 (C4 (Web Text))

Max Activating Token Index: 251

Text #6

Max Range: 10.8638. Min Range: -10.8638

Max Act: 0.1473. Min Act: -0.0000

Data Index: 1115708 (C4 (Web Text))

Max Activating Token Index: 294

Text #7

Max Range: 10.8638. Min Range: -10.8638

Max Act: 0.2935. Min Act: -0.0000

Data Index: 651826 (C4 (Web Text))

Max Activating Token Index: 835

Text #8

Max Range: 10.8638. Min Range: -10.8638

Max Act: 0.2062. Min Act: -0.0000

Data Index: 1588252 (Python Code)

Max Activating Token Index: 550

Text #9

Max Range: 10.8638. Min Range: -10.8638

Max Act: 0.3822. Min Act: -0.0000

Data Index: 1560375 (Python Code)

Max Activating Token Index: 317

Text #10

Max Range: 10.8638. Min Range: -10.8638

Max Act: 0.0382. Min Act: -0.0000

Data Index: 1192949 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 10.8638. Min Range: -10.8638

Max Act: 0.1164. Min Act: -0.0000

Data Index: 162271 (C4 (Web Text))

Max Activating Token Index: 873

Text #12

Max Range: 10.8638. Min Range: -10.8638

Max Act: 0.1044. Min Act: -0.0000

Data Index: 1112349 (C4 (Web Text))

Max Activating Token Index: 9

Text #13

Max Range: 10.8638. Min Range: -10.8638

Max Act: 0.0725. Min Act: -0.0000

Data Index: 550292 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 10.8638. Min Range: -10.8638

Max Act: 0.1005. Min Act: -0.0000

Data Index: 1177593 (C4 (Web Text))

Max Activating Token Index: 805

Text #15

Max Range: 10.8638. Min Range: -10.8638

Max Act: 0.0645. Min Act: -0.0000

Data Index: 1115690 (C4 (Web Text))

Max Activating Token Index: 800

Text #16

Max Range: 10.8638. Min Range: -10.8638

Max Act: 0.0754. Min Act: -0.0000

Data Index: 973565 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 10.8638. Min Range: -10.8638

Max Act: 0.0607. Min Act: -0.0000

Data Index: 1643839 (Python Code)

Max Activating Token Index: 641

Text #18

Max Range: 10.8638. Min Range: -10.8638

Max Act: 0.0714. Min Act: -0.0000

Data Index: 1620703 (Python Code)

Max Activating Token Index: 164

Text #19

Max Range: 10.8638. Min Range: -10.8638

Max Act: 0.0612. Min Act: -0.0000

Data Index: 70477 (C4 (Web Text))

Max Activating Token Index: 110