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

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

Neuron 2322 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4358. Min Range: -0.4358

Max Act: 0.4358. Min Act: -0.0000

Data Index: 892235 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 0.4358. Min Range: -0.4358

Max Act: 0.4025. Min Act: -0.0000

Data Index: 19387 (C4 (Web Text))

Max Activating Token Index: 755

Text #2

Max Range: 0.4358. Min Range: -0.4358

Max Act: 0.3711. Min Act: -0.0000

Data Index: 795071 (C4 (Web Text))

Max Activating Token Index: 922

Text #3

Max Range: 0.4358. Min Range: -0.4358

Max Act: 0.3740. Min Act: -0.0000

Data Index: 172635 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 0.4358. Min Range: -0.4358

Max Act: 0.3496. Min Act: -0.0000

Data Index: 750795 (C4 (Web Text))

Max Activating Token Index: 818

Text #5

Max Range: 0.4358. Min Range: -0.4358

Max Act: 0.3418. Min Act: -0.0000

Data Index: 192730 (C4 (Web Text))

Max Activating Token Index: 419

Text #6

Max Range: 0.4358. Min Range: -0.4358

Max Act: 0.3459. Min Act: -0.0000

Data Index: 449735 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 0.4358. Min Range: -0.4358

Max Act: 0.3563. Min Act: -0.0000

Data Index: 1252445 (C4 (Web Text))

Max Activating Token Index: 329

Text #8

Max Range: 0.4358. Min Range: -0.4358

Max Act: 0.3315. Min Act: -0.0000

Data Index: 263772 (C4 (Web Text))

Max Activating Token Index: 914

Text #9

Max Range: 0.4358. Min Range: -0.4358

Max Act: 0.3395. Min Act: -0.0000

Data Index: 17619 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 0.4358. Min Range: -0.4358

Max Act: 0.3238. Min Act: -0.0000

Data Index: 1221108 (C4 (Web Text))

Max Activating Token Index: 882

Text #11

Max Range: 0.4358. Min Range: -0.4358

Max Act: 0.3003. Min Act: -0.0000

Data Index: 176450 (C4 (Web Text))

Max Activating Token Index: 643

Text #12

Max Range: 0.4358. Min Range: -0.4358

Max Act: 0.2944. Min Act: -0.0000

Data Index: 1207683 (C4 (Web Text))

Max Activating Token Index: 1004

Text #13

Max Range: 0.4358. Min Range: -0.4358

Max Act: 0.2914. Min Act: -0.0000

Data Index: 72054 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 0.4358. Min Range: -0.4358

Max Act: 0.2982. Min Act: -0.0000

Data Index: 1175762 (C4 (Web Text))

Max Activating Token Index: 939

Text #15

Max Range: 0.4358. Min Range: -0.4358

Max Act: 0.2844. Min Act: -0.0000

Data Index: 1262218 (C4 (Web Text))

Max Activating Token Index: 858

Text #16

Max Range: 0.4358. Min Range: -0.4358

Max Act: 0.2936. Min Act: -0.0000

Data Index: 641167 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 0.4358. Min Range: -0.4358

Max Act: 0.3002. Min Act: -0.0000

Data Index: 930968 (C4 (Web Text))

Max Activating Token Index: 231

Text #18

Max Range: 0.4358. Min Range: -0.4358

Max Act: 0.2835. Min Act: -0.0000

Data Index: 554831 (C4 (Web Text))

Max Activating Token Index: 490

Text #19

Max Range: 0.4358. Min Range: -0.4358

Max Act: 0.2870. Min Act: -0.0000

Data Index: 1211446 (C4 (Web Text))

Max Activating Token Index: 105