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

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

Neuron 4470 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.7232. Min Act: -0.0000

Data Index: 1075340 (C4 (Web Text))

Max Activating Token Index: 561

Text #1

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.7216. Min Act: -0.0000

Data Index: 352475 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.7403. Min Act: -0.0000

Data Index: 525965 (C4 (Web Text))

Max Activating Token Index: 978

Text #3

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.7074. Min Act: -0.0000

Data Index: 1083924 (C4 (Web Text))

Max Activating Token Index: 708

Text #4

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.6621. Min Act: -0.0000

Data Index: 10116 (C4 (Web Text))

Max Activating Token Index: 179

Text #5

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.6324. Min Act: -0.0000

Data Index: 523599 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.6634. Min Act: -0.0000

Data Index: 1055841 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.5953. Min Act: -0.0000

Data Index: 276716 (C4 (Web Text))

Max Activating Token Index: 964

Text #8

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.5615. Min Act: -0.0000

Data Index: 887584 (C4 (Web Text))

Max Activating Token Index: 749

Text #9

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.5518. Min Act: -0.0000

Data Index: 1031123 (C4 (Web Text))

Max Activating Token Index: 374

Text #10

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.5103. Min Act: -0.0000

Data Index: 491741 (C4 (Web Text))

Max Activating Token Index: 711

Text #11

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.5349. Min Act: -0.0000

Data Index: 871532 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.4716. Min Act: -0.0000

Data Index: 644221 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.5352. Min Act: -0.0000

Data Index: 502210 (C4 (Web Text))

Max Activating Token Index: 379

Text #14

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.5294. Min Act: -0.0000

Data Index: 876402 (C4 (Web Text))

Max Activating Token Index: 682

Text #15

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.5222. Min Act: -0.0000

Data Index: 692870 (C4 (Web Text))

Max Activating Token Index: 784

Text #16

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.5238. Min Act: -0.0000

Data Index: 1079784 (C4 (Web Text))

Max Activating Token Index: 25

Text #17

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.5096. Min Act: -0.0000

Data Index: 551571 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.4701. Min Act: -0.0000

Data Index: 780814 (C4 (Web Text))

Max Activating Token Index: 243

Text #19

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.4566. Min Act: -0.0000

Data Index: 762332 (C4 (Web Text))

Max Activating Token Index: 58