Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3056 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 20.9679. Min Range: -20.9679

Max Act: 20.9679. Min Act: -0.0001

Data Index: 1162846 (C4 (Web Text))

Max Activating Token Index: 992

Text #1

Max Range: 20.9679. Min Range: -20.9679

Max Act: 20.7121. Min Act: -0.0001

Data Index: 1375202 (Python Code)

Max Activating Token Index: 474

Text #2

Max Range: 20.9679. Min Range: -20.9679

Max Act: 20.0757. Min Act: -0.0001

Data Index: 223540 (C4 (Web Text))

Max Activating Token Index: 639

Text #3

Max Range: 20.9679. Min Range: -20.9679

Max Act: 19.5513. Min Act: -0.0001

Data Index: 716804 (C4 (Web Text))

Max Activating Token Index: 641

Text #4

Max Range: 20.9679. Min Range: -20.9679

Max Act: 19.4435. Min Act: -0.0001

Data Index: 555771 (C4 (Web Text))

Max Activating Token Index: 566

Text #5

Max Range: 20.9679. Min Range: -20.9679

Max Act: 19.3326. Min Act: -0.0001

Data Index: 976675 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 20.9679. Min Range: -20.9679

Max Act: 19.2087. Min Act: -0.0001

Data Index: 642917 (C4 (Web Text))

Max Activating Token Index: 1

Text #7

Max Range: 20.9679. Min Range: -20.9679

Max Act: 19.2087. Min Act: -0.0001

Data Index: 277714 (C4 (Web Text))

Max Activating Token Index: 1

Text #8

Max Range: 20.9679. Min Range: -20.9679

Max Act: 19.3408. Min Act: -0.0001

Data Index: 1343676 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 20.9679. Min Range: -20.9679

Max Act: 19.2159. Min Act: -0.0001

Data Index: 612816 (C4 (Web Text))

Max Activating Token Index: 955

Text #10

Max Range: 20.9679. Min Range: -20.9679

Max Act: 18.8284. Min Act: -0.0001

Data Index: 268377 (C4 (Web Text))

Max Activating Token Index: 602

Text #11

Max Range: 20.9679. Min Range: -20.9679

Max Act: 18.9555. Min Act: -0.0001

Data Index: 307711 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 20.9679. Min Range: -20.9679

Max Act: 18.8222. Min Act: -0.0001

Data Index: 99891 (C4 (Web Text))

Max Activating Token Index: 346

Text #13

Max Range: 20.9679. Min Range: -20.9679

Max Act: 19.0829. Min Act: -0.0001

Data Index: 669810 (C4 (Web Text))

Max Activating Token Index: 564

Text #14

Max Range: 20.9679. Min Range: -20.9679

Max Act: 18.7019. Min Act: -0.0001

Data Index: 586599 (C4 (Web Text))

Max Activating Token Index: 523

Text #15

Max Range: 20.9679. Min Range: -20.9679

Max Act: 18.5894. Min Act: -0.0001

Data Index: 1612318 (Python Code)

Max Activating Token Index: 1020

Text #16

Max Range: 20.9679. Min Range: -20.9679

Max Act: 18.5863. Min Act: -0.0001

Data Index: 1380266 (Python Code)

Max Activating Token Index: 505

Text #17

Max Range: 20.9679. Min Range: -20.9679

Max Act: 18.7076. Min Act: -0.0001

Data Index: 1072433 (C4 (Web Text))

Max Activating Token Index: 756

Text #18

Max Range: 20.9679. Min Range: -20.9679

Max Act: 18.7150. Min Act: -0.0001

Data Index: 1524809 (Python Code)

Max Activating Token Index: 990

Text #19

Max Range: 20.9679. Min Range: -20.9679

Max Act: 18.5849. Min Act: -0.0001

Data Index: 345896 (C4 (Web Text))

Max Activating Token Index: 365