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

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

Neuron 867 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1765. Min Range: -2.1765

Max Act: 2.1719. Min Act: -0.0001

Data Index: 1084872 (C4 (Web Text))

Max Activating Token Index: 314

Text #1

Max Range: 2.1765. Min Range: -2.1765

Max Act: 2.1765. Min Act: -0.0001

Data Index: 1045077 (C4 (Web Text))

Max Activating Token Index: 284

Text #2

Max Range: 2.1765. Min Range: -2.1765

Max Act: 1.5981. Min Act: -0.0001

Data Index: 1279434 (C4 (Web Text))

Max Activating Token Index: 134

Text #3

Max Range: 2.1765. Min Range: -2.1765

Max Act: 1.6839. Min Act: -0.0001

Data Index: 946023 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 2.1765. Min Range: -2.1765

Max Act: 1.6881. Min Act: -0.0001

Data Index: 1134704 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 2.1765. Min Range: -2.1765

Max Act: 1.5022. Min Act: -0.0001

Data Index: 818884 (C4 (Web Text))

Max Activating Token Index: 690

Text #6

Max Range: 2.1765. Min Range: -2.1765

Max Act: 1.4387. Min Act: -0.0001

Data Index: 361545 (C4 (Web Text))

Max Activating Token Index: 575

Text #7

Max Range: 2.1765. Min Range: -2.1765

Max Act: 1.2980. Min Act: -0.0001

Data Index: 1167657 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 2.1765. Min Range: -2.1765

Max Act: 1.4587. Min Act: -0.0001

Data Index: 1279230 (C4 (Web Text))

Max Activating Token Index: 195

Text #9

Max Range: 2.1765. Min Range: -2.1765

Max Act: 1.5710. Min Act: -0.0001

Data Index: 401519 (C4 (Web Text))

Max Activating Token Index: 236

Text #10

Max Range: 2.1765. Min Range: -2.1765

Max Act: 1.5214. Min Act: -0.0001

Data Index: 1078607 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 2.1765. Min Range: -2.1765

Max Act: 1.4524. Min Act: -0.0001

Data Index: 386548 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 2.1765. Min Range: -2.1765

Max Act: 1.4257. Min Act: -0.0001

Data Index: 345596 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 2.1765. Min Range: -2.1765

Max Act: 1.4573. Min Act: -0.0001

Data Index: 948623 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 2.1765. Min Range: -2.1765

Max Act: 1.4282. Min Act: -0.0001

Data Index: 825181 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 2.1765. Min Range: -2.1765

Max Act: 1.4583. Min Act: -0.0001

Data Index: 454926 (C4 (Web Text))

Max Activating Token Index: 235

Text #16

Max Range: 2.1765. Min Range: -2.1765

Max Act: 1.3896. Min Act: -0.0001

Data Index: 962323 (C4 (Web Text))

Max Activating Token Index: 130

Text #17

Max Range: 2.1765. Min Range: -2.1765

Max Act: 1.3940. Min Act: -0.0001

Data Index: 331345 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 2.1765. Min Range: -2.1765

Max Act: 1.5653. Min Act: -0.0001

Data Index: 31211 (C4 (Web Text))

Max Activating Token Index: 327

Text #19

Max Range: 2.1765. Min Range: -2.1765

Max Act: 1.4576. Min Act: -0.0001

Data Index: 973097 (C4 (Web Text))

Max Activating Token Index: 938