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

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

Neuron 760 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: 1.9331. Min Range: -1.9331

Max Act: 1.7795. Min Act: -0.0000

Data Index: 202095 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.9331. Min Act: -0.0000

Data Index: 496142 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.6629. Min Act: -0.0000

Data Index: 1506574 (Python Code)

Max Activating Token Index: 111

Text #3

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.5626. Min Act: -0.0000

Data Index: 279203 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.3452. Min Act: -0.0000

Data Index: 1465398 (Python Code)

Max Activating Token Index: 38

Text #5

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.3486. Min Act: -0.0000

Data Index: 1519258 (Python Code)

Max Activating Token Index: 75

Text #6

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.2684. Min Act: -0.0000

Data Index: 1536126 (Python Code)

Max Activating Token Index: 495

Text #7

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.3612. Min Act: -0.0000

Data Index: 1470555 (Python Code)

Max Activating Token Index: 787

Text #8

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.4070. Min Act: -0.0000

Data Index: 1074539 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.1353. Min Act: -0.0000

Data Index: 1640454 (Python Code)

Max Activating Token Index: 135

Text #10

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.2418. Min Act: -0.0000

Data Index: 1642942 (Python Code)

Max Activating Token Index: 100

Text #11

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.1739. Min Act: -0.0000

Data Index: 936141 (C4 (Web Text))

Max Activating Token Index: 583

Text #12

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.1946. Min Act: -0.0000

Data Index: 1608202 (Python Code)

Max Activating Token Index: 137

Text #13

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.1022. Min Act: -0.0000

Data Index: 1111922 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.3627. Min Act: -0.0000

Data Index: 1504601 (Python Code)

Max Activating Token Index: 760

Text #15

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.2007. Min Act: -0.0000

Data Index: 1562660 (Python Code)

Max Activating Token Index: 220

Text #16

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.2202. Min Act: -0.0000

Data Index: 1292038 (C4 (Web Text))

Max Activating Token Index: 868

Text #17

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.4125. Min Act: -0.0000

Data Index: 455742 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.1419. Min Act: -0.0000

Data Index: 232194 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.1729. Min Act: -0.0000

Data Index: 1440255 (Python Code)

Max Activating Token Index: 602