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

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

Neuron 2127 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.8355. Min Act: -0.0000

Data Index: 1562859 (Python Code)

Max Activating Token Index: 419

Text #1

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.7801. Min Act: -0.0000

Data Index: 1424204 (Python Code)

Max Activating Token Index: 803

Text #2

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.7380. Min Act: -0.0000

Data Index: 1560188 (Python Code)

Max Activating Token Index: 587

Text #3

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.7640. Min Act: -0.0000

Data Index: 1618513 (Python Code)

Max Activating Token Index: 455

Text #4

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.7304. Min Act: -0.0000

Data Index: 1548155 (Python Code)

Max Activating Token Index: 372

Text #5

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.6766. Min Act: -0.0000

Data Index: 1424092 (Python Code)

Max Activating Token Index: 739

Text #6

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.7217. Min Act: -0.0000

Data Index: 1512613 (Python Code)

Max Activating Token Index: 248

Text #7

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.7141. Min Act: -0.0000

Data Index: 1599625 (Python Code)

Max Activating Token Index: 658

Text #8

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.6513. Min Act: -0.0000

Data Index: 1556527 (Python Code)

Max Activating Token Index: 395

Text #9

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.6797. Min Act: -0.0000

Data Index: 1623429 (Python Code)

Max Activating Token Index: 592

Text #10

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.6827. Min Act: -0.0000

Data Index: 1361983 (Python Code)

Max Activating Token Index: 143

Text #11

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.6611. Min Act: -0.0000

Data Index: 1644955 (Python Code)

Max Activating Token Index: 260

Text #12

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.6728. Min Act: -0.0000

Data Index: 1366720 (Python Code)

Max Activating Token Index: 681

Text #13

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.6453. Min Act: -0.0000

Data Index: 1611233 (Python Code)

Max Activating Token Index: 446

Text #14

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.6191. Min Act: -0.0000

Data Index: 1540604 (Python Code)

Max Activating Token Index: 430

Text #15

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.6402. Min Act: -0.0000

Data Index: 1552702 (Python Code)

Max Activating Token Index: 1016

Text #16

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.6646. Min Act: -0.0000

Data Index: 1385693 (Python Code)

Max Activating Token Index: 468

Text #17

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.6365. Min Act: -0.0000

Data Index: 1564877 (Python Code)

Max Activating Token Index: 633

Text #18

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.6589. Min Act: -0.0000

Data Index: 1547921 (Python Code)

Max Activating Token Index: 677

Text #19

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.6381. Min Act: -0.0000

Data Index: 1604965 (Python Code)

Max Activating Token Index: 392