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

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

Neuron 3482 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: 4.0789. Min Range: -4.0789

Max Act: 3.9632. Min Act: -0.0000

Data Index: 984802 (C4 (Web Text))

Max Activating Token Index: 328

Text #1

Max Range: 4.0789. Min Range: -4.0789

Max Act: 4.0466. Min Act: -0.0000

Data Index: 51006 (C4 (Web Text))

Max Activating Token Index: 714

Text #2

Max Range: 4.0789. Min Range: -4.0789

Max Act: 4.0789. Min Act: -0.0000

Data Index: 344553 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 4.0789. Min Range: -4.0789

Max Act: 3.8882. Min Act: -0.0000

Data Index: 480983 (C4 (Web Text))

Max Activating Token Index: 705

Text #4

Max Range: 4.0789. Min Range: -4.0789

Max Act: 3.8214. Min Act: -0.0000

Data Index: 440880 (C4 (Web Text))

Max Activating Token Index: 853

Text #5

Max Range: 4.0789. Min Range: -4.0789

Max Act: 3.7762. Min Act: -0.0000

Data Index: 607666 (C4 (Web Text))

Max Activating Token Index: 1010

Text #6

Max Range: 4.0789. Min Range: -4.0789

Max Act: 3.7377. Min Act: -0.0000

Data Index: 1102034 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 4.0789. Min Range: -4.0789

Max Act: 3.6910. Min Act: -0.0000

Data Index: 1129557 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 4.0789. Min Range: -4.0789

Max Act: 3.6418. Min Act: -0.0000

Data Index: 654437 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 4.0789. Min Range: -4.0789

Max Act: 2.8959. Min Act: -0.0000

Data Index: 280665 (C4 (Web Text))

Max Activating Token Index: 920

Text #10

Max Range: 4.0789. Min Range: -4.0789

Max Act: 2.8050. Min Act: -0.0000

Data Index: 634541 (C4 (Web Text))

Max Activating Token Index: 897

Text #11

Max Range: 4.0789. Min Range: -4.0789

Max Act: 2.7414. Min Act: -0.0001

Data Index: 367899 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 4.0789. Min Range: -4.0789

Max Act: 2.7042. Min Act: -0.0000

Data Index: 270567 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 4.0789. Min Range: -4.0789

Max Act: 2.5590. Min Act: -0.0000

Data Index: 220081 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 4.0789. Min Range: -4.0789

Max Act: 2.6761. Min Act: -0.0000

Data Index: 1134931 (C4 (Web Text))

Max Activating Token Index: 605

Text #15

Max Range: 4.0789. Min Range: -4.0789

Max Act: 2.4839. Min Act: -0.0001

Data Index: 851673 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 4.0789. Min Range: -4.0789

Max Act: 2.6274. Min Act: -0.0000

Data Index: 238103 (C4 (Web Text))

Max Activating Token Index: 1004

Text #17

Max Range: 4.0789. Min Range: -4.0789

Max Act: 2.7577. Min Act: -0.0000

Data Index: 801450 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 4.0789. Min Range: -4.0789

Max Act: 2.6094. Min Act: -0.0000

Data Index: 1339133 (C4 (Web Text))

Max Activating Token Index: 238

Text #19

Max Range: 4.0789. Min Range: -4.0789

Max Act: 2.5867. Min Act: -0.0000

Data Index: 3464 (C4 (Web Text))

Max Activating Token Index: 999