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

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

Neuron 5072 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4642. Min Range: -0.4642

Max Act: 0.4642. Min Act: -0.0000

Data Index: 624546 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 0.4642. Min Range: -0.4642

Max Act: 0.3949. Min Act: -0.0000

Data Index: 477678 (C4 (Web Text))

Max Activating Token Index: 791

Text #2

Max Range: 0.4642. Min Range: -0.4642

Max Act: 0.4078. Min Act: -0.0000

Data Index: 1344019 (C4 (Web Text))

Max Activating Token Index: 4

Text #3

Max Range: 0.4642. Min Range: -0.4642

Max Act: 0.3666. Min Act: -0.0000

Data Index: 626368 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 0.4642. Min Range: -0.4642

Max Act: 0.3371. Min Act: -0.0000

Data Index: 769178 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 0.4642. Min Range: -0.4642

Max Act: 0.3014. Min Act: -0.0000

Data Index: 132515 (C4 (Web Text))

Max Activating Token Index: 370

Text #6

Max Range: 0.4642. Min Range: -0.4642

Max Act: 0.3008. Min Act: -0.0000

Data Index: 356448 (C4 (Web Text))

Max Activating Token Index: 347

Text #7

Max Range: 0.4642. Min Range: -0.4642

Max Act: 0.3112. Min Act: -0.0000

Data Index: 972252 (C4 (Web Text))

Max Activating Token Index: 369

Text #8

Max Range: 0.4642. Min Range: -0.4642

Max Act: 0.2823. Min Act: -0.0000

Data Index: 982810 (C4 (Web Text))

Max Activating Token Index: 429

Text #9

Max Range: 0.4642. Min Range: -0.4642

Max Act: 0.2904. Min Act: -0.0000

Data Index: 44753 (C4 (Web Text))

Max Activating Token Index: 467

Text #10

Max Range: 0.4642. Min Range: -0.4642

Max Act: 0.2754. Min Act: -0.0000

Data Index: 1277172 (C4 (Web Text))

Max Activating Token Index: 644

Text #11

Max Range: 0.4642. Min Range: -0.4642

Max Act: 0.2671. Min Act: -0.0000

Data Index: 440530 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 0.4642. Min Range: -0.4642

Max Act: 0.2409. Min Act: -0.0000

Data Index: 369989 (C4 (Web Text))

Max Activating Token Index: 23

Text #13

Max Range: 0.4642. Min Range: -0.4642

Max Act: 0.2418. Min Act: -0.0000

Data Index: 855006 (C4 (Web Text))

Max Activating Token Index: 991

Text #14

Max Range: 0.4642. Min Range: -0.4642

Max Act: 0.2675. Min Act: -0.0000

Data Index: 1177052 (C4 (Web Text))

Max Activating Token Index: 38

Text #15

Max Range: 0.4642. Min Range: -0.4642

Max Act: 0.2365. Min Act: -0.0000

Data Index: 729108 (C4 (Web Text))

Max Activating Token Index: 712

Text #16

Max Range: 0.4642. Min Range: -0.4642

Max Act: 0.2559. Min Act: -0.0000

Data Index: 262940 (C4 (Web Text))

Max Activating Token Index: 914

Text #17

Max Range: 0.4642. Min Range: -0.4642

Max Act: 0.2451. Min Act: -0.0000

Data Index: 919724 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 0.4642. Min Range: -0.4642

Max Act: 0.2447. Min Act: -0.0000

Data Index: 857896 (C4 (Web Text))

Max Activating Token Index: 722

Text #19

Max Range: 0.4642. Min Range: -0.4642

Max Act: 0.2356. Min Act: -0.0000

Data Index: 323309 (C4 (Web Text))

Max Activating Token Index: 670