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

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

Neuron 745 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3734. Min Act: -0.0000

Data Index: 1514538 (Python Code)

Max Activating Token Index: 724

Text #1

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2687. Min Act: -0.0000

Data Index: 1390787 (Python Code)

Max Activating Token Index: 696

Text #2

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2917. Min Act: -0.0000

Data Index: 1385480 (Python Code)

Max Activating Token Index: 109

Text #3

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2514. Min Act: -0.0000

Data Index: 1389331 (Python Code)

Max Activating Token Index: 692

Text #4

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2258. Min Act: -0.0000

Data Index: 498683 (C4 (Web Text))

Max Activating Token Index: 672

Text #5

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2368. Min Act: -0.0000

Data Index: 344327 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2601. Min Act: -0.0001

Data Index: 1441386 (Python Code)

Max Activating Token Index: 918

Text #7

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2000. Min Act: -0.0000

Data Index: 876467 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.1902. Min Act: -0.0000

Data Index: 227530 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.1829. Min Act: -0.0001

Data Index: 1374599 (Python Code)

Max Activating Token Index: 300

Text #10

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.1937. Min Act: -0.0000

Data Index: 1545354 (Python Code)

Max Activating Token Index: 1012

Text #11

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.1855. Min Act: -0.0001

Data Index: 422660 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.1917. Min Act: -0.0000

Data Index: 925463 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.1751. Min Act: -0.0000

Data Index: 1394644 (Python Code)

Max Activating Token Index: 830

Text #14

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.1643. Min Act: -0.0000

Data Index: 237597 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.1735. Min Act: -0.0000

Data Index: 656794 (C4 (Web Text))

Max Activating Token Index: 85

Text #16

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.1791. Min Act: -0.0000

Data Index: 1407291 (Python Code)

Max Activating Token Index: 1020

Text #17

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.1525. Min Act: -0.0000

Data Index: 280030 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.1699. Min Act: -0.0000

Data Index: 1538974 (Python Code)

Max Activating Token Index: 769

Text #19

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.1523. Min Act: -0.0000

Data Index: 1244775 (C4 (Web Text))

Max Activating Token Index: 260