Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1571 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0743. Min Range: -1.0743

Max Act: 1.0743. Min Act: -0.0002

Data Index: 301133 (C4 (Web Text))

Max Activating Token Index: 964

Text #1

Max Range: 1.0743. Min Range: -1.0743

Max Act: 0.9010. Min Act: -0.0002

Data Index: 732778 (C4 (Web Text))

Max Activating Token Index: 178

Text #2

Max Range: 1.0743. Min Range: -1.0743

Max Act: 1.0129. Min Act: -0.0001

Data Index: 887126 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 1.0743. Min Range: -1.0743

Max Act: 1.0401. Min Act: -0.0002

Data Index: 18887 (C4 (Web Text))

Max Activating Token Index: 962

Text #4

Max Range: 1.0743. Min Range: -1.0743

Max Act: 0.9539. Min Act: -0.0001

Data Index: 480999 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 1.0743. Min Range: -1.0743

Max Act: 0.9830. Min Act: -0.0001

Data Index: 807357 (C4 (Web Text))

Max Activating Token Index: 87

Text #6

Max Range: 1.0743. Min Range: -1.0743

Max Act: 0.9067. Min Act: -0.0001

Data Index: 478535 (C4 (Web Text))

Max Activating Token Index: 544

Text #7

Max Range: 1.0743. Min Range: -1.0743

Max Act: 0.9308. Min Act: -0.0001

Data Index: 986574 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 1.0743. Min Range: -1.0743

Max Act: 0.9333. Min Act: -0.0001

Data Index: 928992 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 1.0743. Min Range: -1.0743

Max Act: 0.8817. Min Act: -0.0001

Data Index: 337646 (C4 (Web Text))

Max Activating Token Index: 859

Text #10

Max Range: 1.0743. Min Range: -1.0743

Max Act: 0.9582. Min Act: -0.0002

Data Index: 822983 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 1.0743. Min Range: -1.0743

Max Act: 0.9315. Min Act: -0.0001

Data Index: 602334 (C4 (Web Text))

Max Activating Token Index: 809

Text #12

Max Range: 1.0743. Min Range: -1.0743

Max Act: 0.8595. Min Act: -0.0001

Data Index: 828113 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 1.0743. Min Range: -1.0743

Max Act: 0.9371. Min Act: -0.0001

Data Index: 410099 (C4 (Web Text))

Max Activating Token Index: 526

Text #14

Max Range: 1.0743. Min Range: -1.0743

Max Act: 0.9619. Min Act: -0.0001

Data Index: 1303812 (C4 (Web Text))

Max Activating Token Index: 502

Text #15

Max Range: 1.0743. Min Range: -1.0743

Max Act: 0.7733. Min Act: -0.0002

Data Index: 1277406 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 1.0743. Min Range: -1.0743

Max Act: 0.9000. Min Act: -0.0001

Data Index: 859981 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 1.0743. Min Range: -1.0743

Max Act: 0.8990. Min Act: -0.0001

Data Index: 115720 (C4 (Web Text))

Max Activating Token Index: 801

Text #18

Max Range: 1.0743. Min Range: -1.0743

Max Act: 0.8581. Min Act: -0.0001

Data Index: 412750 (C4 (Web Text))

Max Activating Token Index: 231

Text #19

Max Range: 1.0743. Min Range: -1.0743

Max Act: 0.8864. Min Act: -0.0001

Data Index: 977440 (C4 (Web Text))

Max Activating Token Index: 1002