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

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

Neuron 5648 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: 2.9354. Min Range: -2.9354

Max Act: 2.8810. Min Act: -0.0000

Data Index: 1587598 (Python Code)

Max Activating Token Index: 623

Text #1

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.9354. Min Act: -0.0000

Data Index: 777109 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.9262. Min Act: -0.0000

Data Index: 1201025 (C4 (Web Text))

Max Activating Token Index: 458

Text #3

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.9087. Min Act: -0.0000

Data Index: 382398 (C4 (Web Text))

Max Activating Token Index: 485

Text #4

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.8797. Min Act: -0.0000

Data Index: 918110 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.8336. Min Act: -0.0000

Data Index: 49670 (C4 (Web Text))

Max Activating Token Index: 993

Text #6

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.7659. Min Act: -0.0000

Data Index: 637595 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.6102. Min Act: -0.0000

Data Index: 1585710 (Python Code)

Max Activating Token Index: 550

Text #8

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.7362. Min Act: -0.0000

Data Index: 885409 (C4 (Web Text))

Max Activating Token Index: 948

Text #9

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.5273. Min Act: -0.0000

Data Index: 1144064 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.5436. Min Act: -0.0000

Data Index: 118553 (C4 (Web Text))

Max Activating Token Index: 679

Text #11

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.5823. Min Act: -0.0000

Data Index: 1316425 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.5587. Min Act: -0.0000

Data Index: 1459241 (Python Code)

Max Activating Token Index: 893

Text #13

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.5402. Min Act: -0.0000

Data Index: 1628942 (Python Code)

Max Activating Token Index: 819

Text #14

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.1863. Min Act: -0.0000

Data Index: 1388353 (Python Code)

Max Activating Token Index: 632

Text #15

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.5290. Min Act: -0.0000

Data Index: 1466662 (Python Code)

Max Activating Token Index: 862

Text #16

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.3966. Min Act: -0.0000

Data Index: 1419742 (Python Code)

Max Activating Token Index: 253

Text #17

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.3579. Min Act: -0.0000

Data Index: 1465510 (Python Code)

Max Activating Token Index: 877

Text #18

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.3367. Min Act: -0.0000

Data Index: 1640560 (Python Code)

Max Activating Token Index: 613

Text #19

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.1575. Min Act: -0.0000

Data Index: 1571734 (Python Code)

Max Activating Token Index: 298