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

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

Neuron 2663 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9582. Min Range: -0.9582

Max Act: 0.9582. Min Act: -0.0000

Data Index: 1640625 (Python Code)

Max Activating Token Index: 161

Text #1

Max Range: 0.9582. Min Range: -0.9582

Max Act: 0.8356. Min Act: -0.0000

Data Index: 1404172 (Python Code)

Max Activating Token Index: 188

Text #2

Max Range: 0.9582. Min Range: -0.9582

Max Act: 0.8247. Min Act: -0.0000

Data Index: 876805 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 0.9582. Min Range: -0.9582

Max Act: 0.7733. Min Act: -0.0000

Data Index: 1491846 (Python Code)

Max Activating Token Index: 992

Text #4

Max Range: 0.9582. Min Range: -0.9582

Max Act: 0.8907. Min Act: -0.0000

Data Index: 1250422 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 0.9582. Min Range: -0.9582

Max Act: 0.7588. Min Act: -0.0000

Data Index: 1603739 (Python Code)

Max Activating Token Index: 41

Text #6

Max Range: 0.9582. Min Range: -0.9582

Max Act: 0.7813. Min Act: -0.0000

Data Index: 1468548 (Python Code)

Max Activating Token Index: 31

Text #7

Max Range: 0.9582. Min Range: -0.9582

Max Act: 0.7697. Min Act: -0.0000

Data Index: 1584636 (Python Code)

Max Activating Token Index: 284

Text #8

Max Range: 0.9582. Min Range: -0.9582

Max Act: 0.6914. Min Act: -0.0000

Data Index: 765484 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 0.9582. Min Range: -0.9582

Max Act: 0.7491. Min Act: -0.0000

Data Index: 1571693 (Python Code)

Max Activating Token Index: 296

Text #10

Max Range: 0.9582. Min Range: -0.9582

Max Act: 0.7716. Min Act: -0.0000

Data Index: 1418266 (Python Code)

Max Activating Token Index: 371

Text #11

Max Range: 0.9582. Min Range: -0.9582

Max Act: 0.7312. Min Act: -0.0000

Data Index: 498528 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 0.9582. Min Range: -0.9582

Max Act: 0.7007. Min Act: -0.0000

Data Index: 995480 (C4 (Web Text))

Max Activating Token Index: 353

Text #13

Max Range: 0.9582. Min Range: -0.9582

Max Act: 0.6984. Min Act: -0.0000

Data Index: 1174816 (C4 (Web Text))

Max Activating Token Index: 996

Text #14

Max Range: 0.9582. Min Range: -0.9582

Max Act: 0.7514. Min Act: -0.0000

Data Index: 591532 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 0.9582. Min Range: -0.9582

Max Act: 0.7140. Min Act: -0.0000

Data Index: 1426297 (Python Code)

Max Activating Token Index: 360

Text #16

Max Range: 0.9582. Min Range: -0.9582

Max Act: 0.7241. Min Act: -0.0000

Data Index: 115551 (C4 (Web Text))

Max Activating Token Index: 871

Text #17

Max Range: 0.9582. Min Range: -0.9582

Max Act: 0.6874. Min Act: -0.0000

Data Index: 310708 (C4 (Web Text))

Max Activating Token Index: 938

Text #18

Max Range: 0.9582. Min Range: -0.9582

Max Act: 0.7038. Min Act: -0.0000

Data Index: 1194535 (C4 (Web Text))

Max Activating Token Index: 916

Text #19

Max Range: 0.9582. Min Range: -0.9582

Max Act: 0.6893. Min Act: -0.0000

Data Index: 145711 (C4 (Web Text))

Max Activating Token Index: 524