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

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

Neuron 1366 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: 5.8230. Min Range: -5.8230

Max Act: 5.7427. Min Act: -0.0000

Data Index: 517857 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 5.8230. Min Range: -5.8230

Max Act: 5.8230. Min Act: -0.0000

Data Index: 202820 (C4 (Web Text))

Max Activating Token Index: 212

Text #2

Max Range: 5.8230. Min Range: -5.8230

Max Act: 5.3037. Min Act: -0.0000

Data Index: 711311 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 5.8230. Min Range: -5.8230

Max Act: 4.7618. Min Act: -0.0000

Data Index: 549167 (C4 (Web Text))

Max Activating Token Index: 644

Text #4

Max Range: 5.8230. Min Range: -5.8230

Max Act: 4.7668. Min Act: -0.0000

Data Index: 568082 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 5.8230. Min Range: -5.8230

Max Act: 4.4332. Min Act: -0.0000

Data Index: 1044541 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 5.8230. Min Range: -5.8230

Max Act: 4.2518. Min Act: -0.0000

Data Index: 1295373 (C4 (Web Text))

Max Activating Token Index: 366

Text #7

Max Range: 5.8230. Min Range: -5.8230

Max Act: 4.3467. Min Act: -0.0000

Data Index: 1150800 (C4 (Web Text))

Max Activating Token Index: 228

Text #8

Max Range: 5.8230. Min Range: -5.8230

Max Act: 4.1047. Min Act: -0.0000

Data Index: 147439 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 5.8230. Min Range: -5.8230

Max Act: 4.1204. Min Act: -0.0000

Data Index: 510570 (C4 (Web Text))

Max Activating Token Index: 339

Text #10

Max Range: 5.8230. Min Range: -5.8230

Max Act: 4.2392. Min Act: -0.0000

Data Index: 12807 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 5.8230. Min Range: -5.8230

Max Act: 4.3554. Min Act: -0.0000

Data Index: 1199379 (C4 (Web Text))

Max Activating Token Index: 823

Text #12

Max Range: 5.8230. Min Range: -5.8230

Max Act: 4.0813. Min Act: -0.0000

Data Index: 227894 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 5.8230. Min Range: -5.8230

Max Act: 4.1576. Min Act: -0.0000

Data Index: 492526 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 5.8230. Min Range: -5.8230

Max Act: 3.7861. Min Act: -0.0000

Data Index: 190590 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 5.8230. Min Range: -5.8230

Max Act: 3.8597. Min Act: -0.0000

Data Index: 574772 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 5.8230. Min Range: -5.8230

Max Act: 3.8176. Min Act: -0.0000

Data Index: 400200 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 5.8230. Min Range: -5.8230

Max Act: 3.5708. Min Act: -0.0000

Data Index: 738709 (C4 (Web Text))

Max Activating Token Index: 379

Text #18

Max Range: 5.8230. Min Range: -5.8230

Max Act: 3.6770. Min Act: -0.0000

Data Index: 102501 (C4 (Web Text))

Max Activating Token Index: 327

Text #19

Max Range: 5.8230. Min Range: -5.8230

Max Act: 3.7013. Min Act: -0.0000

Data Index: 292888 (C4 (Web Text))

Max Activating Token Index: 562