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

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

Neuron 701 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3802. Min Range: -0.3802

Max Act: 0.3802. Min Act: -0.0000

Data Index: 1406582 (Python Code)

Max Activating Token Index: 541

Text #1

Max Range: 0.3802. Min Range: -0.3802

Max Act: 0.3207. Min Act: -0.0000

Data Index: 1382652 (Python Code)

Max Activating Token Index: 249

Text #2

Max Range: 0.3802. Min Range: -0.3802

Max Act: 0.3105. Min Act: -0.0000

Data Index: 355267 (C4 (Web Text))

Max Activating Token Index: 209

Text #3

Max Range: 0.3802. Min Range: -0.3802

Max Act: 0.3078. Min Act: -0.0000

Data Index: 1508965 (Python Code)

Max Activating Token Index: 41

Text #4

Max Range: 0.3802. Min Range: -0.3802

Max Act: 0.2867. Min Act: -0.0000

Data Index: 1622729 (Python Code)

Max Activating Token Index: 973

Text #5

Max Range: 0.3802. Min Range: -0.3802

Max Act: 0.2728. Min Act: -0.0000

Data Index: 1641628 (Python Code)

Max Activating Token Index: 193

Text #6

Max Range: 0.3802. Min Range: -0.3802

Max Act: 0.2692. Min Act: -0.0000

Data Index: 1509933 (Python Code)

Max Activating Token Index: 215

Text #7

Max Range: 0.3802. Min Range: -0.3802

Max Act: 0.2815. Min Act: -0.0000

Data Index: 1401643 (Python Code)

Max Activating Token Index: 80

Text #8

Max Range: 0.3802. Min Range: -0.3802

Max Act: 0.2567. Min Act: -0.0000

Data Index: 1397616 (Python Code)

Max Activating Token Index: 390

Text #9

Max Range: 0.3802. Min Range: -0.3802

Max Act: 0.2764. Min Act: -0.0000

Data Index: 913372 (C4 (Web Text))

Max Activating Token Index: 555

Text #10

Max Range: 0.3802. Min Range: -0.3802

Max Act: 0.2690. Min Act: -0.0000

Data Index: 1298496 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 0.3802. Min Range: -0.3802

Max Act: 0.2682. Min Act: -0.0000

Data Index: 1609849 (Python Code)

Max Activating Token Index: 364

Text #12

Max Range: 0.3802. Min Range: -0.3802

Max Act: 0.2272. Min Act: -0.0000

Data Index: 1567826 (Python Code)

Max Activating Token Index: 62

Text #13

Max Range: 0.3802. Min Range: -0.3802

Max Act: 0.2503. Min Act: -0.0000

Data Index: 1546190 (Python Code)

Max Activating Token Index: 496

Text #14

Max Range: 0.3802. Min Range: -0.3802

Max Act: 0.2293. Min Act: -0.0000

Data Index: 1524292 (Python Code)

Max Activating Token Index: 686

Text #15

Max Range: 0.3802. Min Range: -0.3802

Max Act: 0.2252. Min Act: -0.0000

Data Index: 1578425 (Python Code)

Max Activating Token Index: 258

Text #16

Max Range: 0.3802. Min Range: -0.3802

Max Act: 0.2760. Min Act: -0.0000

Data Index: 1589675 (Python Code)

Max Activating Token Index: 814

Text #17

Max Range: 0.3802. Min Range: -0.3802

Max Act: 0.2103. Min Act: -0.0000

Data Index: 1488111 (Python Code)

Max Activating Token Index: 411

Text #18

Max Range: 0.3802. Min Range: -0.3802

Max Act: 0.2112. Min Act: -0.0000

Data Index: 1413640 (Python Code)

Max Activating Token Index: 371

Text #19

Max Range: 0.3802. Min Range: -0.3802

Max Act: 0.1998. Min Act: -0.0000

Data Index: 1635174 (Python Code)

Max Activating Token Index: 1005