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

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

Neuron 5505 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0745. Min Act: -0.0002

Data Index: 15676 (C4 (Web Text))

Max Activating Token Index: 169

Text #1

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0576. Min Act: -0.0002

Data Index: 1132525 (C4 (Web Text))

Max Activating Token Index: 981

Text #2

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0527. Min Act: -0.0002

Data Index: 994654 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0487. Min Act: -0.0002

Data Index: 192809 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0473. Min Act: -0.0002

Data Index: 893019 (C4 (Web Text))

Max Activating Token Index: 306

Text #5

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0450. Min Act: -0.0002

Data Index: 505604 (C4 (Web Text))

Max Activating Token Index: 753

Text #6

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0464. Min Act: -0.0002

Data Index: 551977 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0429. Min Act: -0.0002

Data Index: 918794 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0430. Min Act: -0.0002

Data Index: 658517 (C4 (Web Text))

Max Activating Token Index: 690

Text #9

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0427. Min Act: -0.0002

Data Index: 1110479 (C4 (Web Text))

Max Activating Token Index: 649

Text #10

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0415. Min Act: -0.0002

Data Index: 99723 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0439. Min Act: -0.0002

Data Index: 168756 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0430. Min Act: -0.0002

Data Index: 768347 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0425. Min Act: -0.0002

Data Index: 134937 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0438. Min Act: -0.0002

Data Index: 487752 (C4 (Web Text))

Max Activating Token Index: 464

Text #15

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0428. Min Act: -0.0002

Data Index: 46569 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0435. Min Act: -0.0002

Data Index: 157519 (C4 (Web Text))

Max Activating Token Index: 809

Text #17

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0417. Min Act: -0.0002

Data Index: 478883 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0437. Min Act: -0.0002

Data Index: 322780 (C4 (Web Text))

Max Activating Token Index: 805

Text #19

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0423. Min Act: -0.0002

Data Index: 246102 (C4 (Web Text))

Max Activating Token Index: 536