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

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

Neuron 54 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: 0.8509. Min Range: -0.8509

Max Act: 0.8509. Min Act: -0.0000

Data Index: 1106505 (C4 (Web Text))

Max Activating Token Index: 179

Text #1

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.6056. Min Act: -0.0000

Data Index: 808364 (C4 (Web Text))

Max Activating Token Index: 574

Text #2

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.5382. Min Act: -0.0000

Data Index: 957454 (C4 (Web Text))

Max Activating Token Index: 169

Text #3

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.5746. Min Act: -0.0000

Data Index: 844278 (C4 (Web Text))

Max Activating Token Index: 140

Text #4

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.5644. Min Act: -0.0000

Data Index: 1526040 (Python Code)

Max Activating Token Index: 417

Text #5

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.5167. Min Act: -0.0000

Data Index: 1343941 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.5660. Min Act: -0.0000

Data Index: 272540 (C4 (Web Text))

Max Activating Token Index: 828

Text #7

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.5749. Min Act: -0.0000

Data Index: 355712 (C4 (Web Text))

Max Activating Token Index: 724

Text #8

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.5304. Min Act: -0.0000

Data Index: 1480071 (Python Code)

Max Activating Token Index: 514

Text #9

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.5236. Min Act: -0.0000

Data Index: 1380372 (Python Code)

Max Activating Token Index: 595

Text #10

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.5499. Min Act: 0.0000

Data Index: 945901 (C4 (Web Text))

Max Activating Token Index: 499

Text #11

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.5501. Min Act: 0.0000

Data Index: 877773 (C4 (Web Text))

Max Activating Token Index: 405

Text #12

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.5416. Min Act: -0.0000

Data Index: 452009 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.5067. Min Act: -0.0000

Data Index: 531459 (C4 (Web Text))

Max Activating Token Index: 973

Text #14

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.5276. Min Act: -0.0000

Data Index: 448572 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.4985. Min Act: -0.0000

Data Index: 617696 (C4 (Web Text))

Max Activating Token Index: 507

Text #16

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.5050. Min Act: -0.0000

Data Index: 1261415 (C4 (Web Text))

Max Activating Token Index: 652

Text #17

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.5276. Min Act: -0.0000

Data Index: 272118 (C4 (Web Text))

Max Activating Token Index: 572

Text #18

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.4767. Min Act: -0.0000

Data Index: 210248 (C4 (Web Text))

Max Activating Token Index: 559

Text #19

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.5039. Min Act: -0.0000

Data Index: 1449710 (Python Code)

Max Activating Token Index: 315