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

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

Neuron 278 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.7588. Min Act: -0.0003

Data Index: 615263 (C4 (Web Text))

Max Activating Token Index: 463

Text #1

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.7757. Min Act: -0.0003

Data Index: 1162545 (C4 (Web Text))

Max Activating Token Index: 401

Text #2

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.7897. Min Act: -0.0003

Data Index: 673806 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.6016. Min Act: -0.0003

Data Index: 674438 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.6409. Min Act: -0.0003

Data Index: 574603 (C4 (Web Text))

Max Activating Token Index: 599

Text #5

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.6955. Min Act: -0.0003

Data Index: 1201921 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.6426. Min Act: -0.0003

Data Index: 826054 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.6079. Min Act: -0.0003

Data Index: 72502 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.5836. Min Act: -0.0003

Data Index: 349769 (C4 (Web Text))

Max Activating Token Index: 752

Text #9

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.6458. Min Act: -0.0003

Data Index: 1139339 (C4 (Web Text))

Max Activating Token Index: 111

Text #10

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.6233. Min Act: -0.0003

Data Index: 1211029 (C4 (Web Text))

Max Activating Token Index: 250

Text #11

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.6126. Min Act: -0.0003

Data Index: 530454 (C4 (Web Text))

Max Activating Token Index: 722

Text #12

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.5610. Min Act: -0.0003

Data Index: 1185584 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.6130. Min Act: -0.0003

Data Index: 470966 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.6117. Min Act: -0.0003

Data Index: 157226 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.4660. Min Act: -0.0003

Data Index: 1190410 (C4 (Web Text))

Max Activating Token Index: 934

Text #16

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.5667. Min Act: -0.0003

Data Index: 760446 (C4 (Web Text))

Max Activating Token Index: 264

Text #17

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.5140. Min Act: -0.0003

Data Index: 961695 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.6938. Min Act: -0.0003

Data Index: 415420 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.6154. Min Act: -0.0003

Data Index: 229167 (C4 (Web Text))

Max Activating Token Index: 804