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

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

Neuron 1705 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1352. Min Range: -1.1352

Max Act: 1.1352. Min Act: -0.0000

Data Index: 1049582 (C4 (Web Text))

Max Activating Token Index: 408

Text #1

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.9684. Min Act: -0.0000

Data Index: 200808 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.7728. Min Act: -0.0000

Data Index: 48609 (C4 (Web Text))

Max Activating Token Index: 436

Text #3

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.7636. Min Act: -0.0000

Data Index: 686790 (C4 (Web Text))

Max Activating Token Index: 644

Text #4

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.7441. Min Act: -0.0000

Data Index: 1048043 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.6507. Min Act: -0.0000

Data Index: 1181531 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.6533. Min Act: -0.0000

Data Index: 201923 (C4 (Web Text))

Max Activating Token Index: 526

Text #7

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.6412. Min Act: -0.0000

Data Index: 965592 (C4 (Web Text))

Max Activating Token Index: 1017

Text #8

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.5523. Min Act: -0.0000

Data Index: 1342273 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.5447. Min Act: -0.0000

Data Index: 1459222 (Python Code)

Max Activating Token Index: 557

Text #10

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.5347. Min Act: -0.0000

Data Index: 817847 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.5453. Min Act: -0.0000

Data Index: 481880 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.5444. Min Act: -0.0000

Data Index: 1396180 (Python Code)

Max Activating Token Index: 424

Text #13

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.5431. Min Act: -0.0000

Data Index: 706005 (C4 (Web Text))

Max Activating Token Index: 145

Text #14

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.5293. Min Act: -0.0000

Data Index: 408082 (C4 (Web Text))

Max Activating Token Index: 573

Text #15

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.5696. Min Act: -0.0000

Data Index: 377773 (C4 (Web Text))

Max Activating Token Index: 297

Text #16

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.5084. Min Act: -0.0000

Data Index: 1540201 (Python Code)

Max Activating Token Index: 198

Text #17

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.4849. Min Act: -0.0000

Data Index: 296611 (C4 (Web Text))

Max Activating Token Index: 386

Text #18

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.4521. Min Act: -0.0000

Data Index: 345188 (C4 (Web Text))

Max Activating Token Index: 190

Text #19

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.4725. Min Act: -0.0000

Data Index: 489349 (C4 (Web Text))

Max Activating Token Index: 626