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

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

Neuron 4193 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.8320. Min Act: -0.0000

Data Index: 680579 (C4 (Web Text))

Max Activating Token Index: 677

Text #1

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7245. Min Act: -0.0000

Data Index: 703594 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6940. Min Act: -0.0000

Data Index: 612920 (C4 (Web Text))

Max Activating Token Index: 860

Text #3

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7189. Min Act: -0.0000

Data Index: 735869 (C4 (Web Text))

Max Activating Token Index: 768

Text #4

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6384. Min Act: 0.0000

Data Index: 409818 (C4 (Web Text))

Max Activating Token Index: 392

Text #5

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6657. Min Act: -0.0000

Data Index: 890332 (C4 (Web Text))

Max Activating Token Index: 318

Text #6

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6189. Min Act: -0.0000

Data Index: 761213 (C4 (Web Text))

Max Activating Token Index: 959

Text #7

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6173. Min Act: -0.0000

Data Index: 308501 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6177. Min Act: -0.0000

Data Index: 975188 (C4 (Web Text))

Max Activating Token Index: 621

Text #9

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.5819. Min Act: -0.0000

Data Index: 592522 (C4 (Web Text))

Max Activating Token Index: 700

Text #10

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.5865. Min Act: 0.0000

Data Index: 1203432 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.5790. Min Act: -0.0000

Data Index: 361115 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.5728. Min Act: -0.0000

Data Index: 1288438 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.5608. Min Act: -0.0000

Data Index: 258863 (C4 (Web Text))

Max Activating Token Index: 222

Text #14

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.5618. Min Act: -0.0000

Data Index: 295308 (C4 (Web Text))

Max Activating Token Index: 276

Text #15

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.5271. Min Act: 0.0000

Data Index: 1263222 (C4 (Web Text))

Max Activating Token Index: 543

Text #16

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.5549. Min Act: -0.0000

Data Index: 854582 (C4 (Web Text))

Max Activating Token Index: 934

Text #17

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.5544. Min Act: -0.0000

Data Index: 1330473 (C4 (Web Text))

Max Activating Token Index: 722

Text #18

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.5501. Min Act: -0.0000

Data Index: 1358604 (C4 (Web Text))

Max Activating Token Index: 141

Text #19

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.5433. Min Act: -0.0000

Data Index: 1209013 (C4 (Web Text))

Max Activating Token Index: 121