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

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

Neuron 4385 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7453. Min Range: -5.7453

Max Act: 5.5568. Min Act: -0.0000

Data Index: 1526665 (Python Code)

Max Activating Token Index: 651

Text #1

Max Range: 5.7453. Min Range: -5.7453

Max Act: 5.7453. Min Act: -0.0000

Data Index: 1406697 (Python Code)

Max Activating Token Index: 604

Text #2

Max Range: 5.7453. Min Range: -5.7453

Max Act: 5.1424. Min Act: -0.0000

Data Index: 1387473 (Python Code)

Max Activating Token Index: 934

Text #3

Max Range: 5.7453. Min Range: -5.7453

Max Act: 5.5794. Min Act: -0.0000

Data Index: 1620906 (Python Code)

Max Activating Token Index: 763

Text #4

Max Range: 5.7453. Min Range: -5.7453

Max Act: 4.6246. Min Act: -0.0000

Data Index: 1499716 (Python Code)

Max Activating Token Index: 244

Text #5

Max Range: 5.7453. Min Range: -5.7453

Max Act: 4.3972. Min Act: -0.0000

Data Index: 1611325 (Python Code)

Max Activating Token Index: 267

Text #6

Max Range: 5.7453. Min Range: -5.7453

Max Act: 4.2540. Min Act: -0.0000

Data Index: 1370074 (Python Code)

Max Activating Token Index: 771

Text #7

Max Range: 5.7453. Min Range: -5.7453

Max Act: 3.8948. Min Act: -0.0000

Data Index: 1539773 (Python Code)

Max Activating Token Index: 571

Text #8

Max Range: 5.7453. Min Range: -5.7453

Max Act: 4.0812. Min Act: -0.0000

Data Index: 1608398 (Python Code)

Max Activating Token Index: 625

Text #9

Max Range: 5.7453. Min Range: -5.7453

Max Act: 3.8485. Min Act: -0.0000

Data Index: 1424343 (Python Code)

Max Activating Token Index: 319

Text #10

Max Range: 5.7453. Min Range: -5.7453

Max Act: 3.1344. Min Act: -0.0000

Data Index: 1395675 (Python Code)

Max Activating Token Index: 44

Text #11

Max Range: 5.7453. Min Range: -5.7453

Max Act: 2.8162. Min Act: -0.0000

Data Index: 1628766 (Python Code)

Max Activating Token Index: 161

Text #12

Max Range: 5.7453. Min Range: -5.7453

Max Act: 2.5481. Min Act: -0.0000

Data Index: 1563270 (Python Code)

Max Activating Token Index: 49

Text #13

Max Range: 5.7453. Min Range: -5.7453

Max Act: 2.6904. Min Act: -0.0000

Data Index: 1376845 (Python Code)

Max Activating Token Index: 32

Text #14

Max Range: 5.7453. Min Range: -5.7453

Max Act: 2.5487. Min Act: -0.0000

Data Index: 1632490 (Python Code)

Max Activating Token Index: 759

Text #15

Max Range: 5.7453. Min Range: -5.7453

Max Act: 2.4908. Min Act: -0.0000

Data Index: 492280 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 5.7453. Min Range: -5.7453

Max Act: 2.4620. Min Act: -0.0000

Data Index: 783480 (C4 (Web Text))

Max Activating Token Index: 986

Text #17

Max Range: 5.7453. Min Range: -5.7453

Max Act: 2.1560. Min Act: -0.0000

Data Index: 797889 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 5.7453. Min Range: -5.7453

Max Act: 2.3549. Min Act: -0.0000

Data Index: 1413864 (Python Code)

Max Activating Token Index: 972

Text #19

Max Range: 5.7453. Min Range: -5.7453

Max Act: 2.3441. Min Act: -0.0000

Data Index: 1484197 (Python Code)

Max Activating Token Index: 273