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

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

Neuron 1914 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.3074. Min Act: -0.0001

Data Index: 939545 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.2368. Min Act: -0.0001

Data Index: 64788 (C4 (Web Text))

Max Activating Token Index: 305

Text #2

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.3948. Min Act: -0.0001

Data Index: 1254422 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 3.5800. Min Range: -3.5800

Max Act: 2.9308. Min Act: -0.0001

Data Index: 230712 (C4 (Web Text))

Max Activating Token Index: 54

Text #4

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.2224. Min Act: -0.0001

Data Index: 965325 (C4 (Web Text))

Max Activating Token Index: 172

Text #5

Max Range: 3.5800. Min Range: -3.5800

Max Act: 2.9608. Min Act: -0.0001

Data Index: 830373 (C4 (Web Text))

Max Activating Token Index: 818

Text #6

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.0551. Min Act: -0.0001

Data Index: 1357293 (C4 (Web Text))

Max Activating Token Index: 349

Text #7

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.1687. Min Act: -0.0001

Data Index: 86624 (C4 (Web Text))

Max Activating Token Index: 140

Text #8

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.5800. Min Act: -0.0001

Data Index: 1069683 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 3.5800. Min Range: -3.5800

Max Act: 2.9542. Min Act: -0.0001

Data Index: 50788 (C4 (Web Text))

Max Activating Token Index: 683

Text #10

Max Range: 3.5800. Min Range: -3.5800

Max Act: 2.6661. Min Act: -0.0001

Data Index: 844593 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 3.5800. Min Range: -3.5800

Max Act: 2.6149. Min Act: -0.0001

Data Index: 814313 (C4 (Web Text))

Max Activating Token Index: 983

Text #12

Max Range: 3.5800. Min Range: -3.5800

Max Act: 2.5997. Min Act: -0.0001

Data Index: 1212789 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 3.5800. Min Range: -3.5800

Max Act: 2.5502. Min Act: -0.0001

Data Index: 402694 (C4 (Web Text))

Max Activating Token Index: 505

Text #14

Max Range: 3.5800. Min Range: -3.5800

Max Act: 2.5383. Min Act: -0.0001

Data Index: 1352741 (C4 (Web Text))

Max Activating Token Index: 642

Text #15

Max Range: 3.5800. Min Range: -3.5800

Max Act: 2.3068. Min Act: -0.0000

Data Index: 560432 (C4 (Web Text))

Max Activating Token Index: 602

Text #16

Max Range: 3.5800. Min Range: -3.5800

Max Act: 2.2741. Min Act: -0.0001

Data Index: 897023 (C4 (Web Text))

Max Activating Token Index: 834

Text #17

Max Range: 3.5800. Min Range: -3.5800

Max Act: 2.3492. Min Act: -0.0001

Data Index: 939143 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 3.5800. Min Range: -3.5800

Max Act: 2.3207. Min Act: -0.0001

Data Index: 657984 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 3.5800. Min Range: -3.5800

Max Act: 2.1859. Min Act: -0.0001

Data Index: 62839 (C4 (Web Text))

Max Activating Token Index: 946