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

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

Neuron 195 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0570. Min Range: -1.0570

Max Act: 1.0570. Min Act: -0.0001

Data Index: 100539 (C4 (Web Text))

Max Activating Token Index: 686

Text #1

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.9646. Min Act: -0.0001

Data Index: 305793 (C4 (Web Text))

Max Activating Token Index: 959

Text #2

Max Range: 1.0570. Min Range: -1.0570

Max Act: 1.0151. Min Act: -0.0001

Data Index: 716727 (C4 (Web Text))

Max Activating Token Index: 818

Text #3

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.9397. Min Act: -0.0001

Data Index: 386945 (C4 (Web Text))

Max Activating Token Index: 42

Text #4

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.8306. Min Act: -0.0001

Data Index: 636773 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.8552. Min Act: -0.0001

Data Index: 624071 (C4 (Web Text))

Max Activating Token Index: 487

Text #6

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.8953. Min Act: -0.0001

Data Index: 888831 (C4 (Web Text))

Max Activating Token Index: 706

Text #7

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.8283. Min Act: -0.0001

Data Index: 1333354 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.8281. Min Act: -0.0001

Data Index: 690608 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.8365. Min Act: -0.0001

Data Index: 373566 (C4 (Web Text))

Max Activating Token Index: 173

Text #10

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.8097. Min Act: -0.0001

Data Index: 1226884 (C4 (Web Text))

Max Activating Token Index: 975

Text #11

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.8098. Min Act: -0.0001

Data Index: 859890 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.8004. Min Act: -0.0001

Data Index: 16799 (C4 (Web Text))

Max Activating Token Index: 541

Text #13

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.7958. Min Act: -0.0001

Data Index: 95830 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.7839. Min Act: -0.0001

Data Index: 667222 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.7798. Min Act: -0.0001

Data Index: 152109 (C4 (Web Text))

Max Activating Token Index: 558

Text #16

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.7888. Min Act: -0.0001

Data Index: 876700 (C4 (Web Text))

Max Activating Token Index: 621

Text #17

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.7506. Min Act: -0.0001

Data Index: 293223 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.7454. Min Act: -0.0001

Data Index: 174043 (C4 (Web Text))

Max Activating Token Index: 980

Text #19

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.7428. Min Act: -0.0001

Data Index: 835700 (C4 (Web Text))

Max Activating Token Index: 627