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

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

Neuron 5234 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7428. Min Range: -4.7428

Max Act: 4.7428. Min Act: -0.0000

Data Index: 487990 (C4 (Web Text))

Max Activating Token Index: 526

Text #1

Max Range: 4.7428. Min Range: -4.7428

Max Act: 4.2630. Min Act: -0.0000

Data Index: 1376224 (Python Code)

Max Activating Token Index: 6

Text #2

Max Range: 4.7428. Min Range: -4.7428

Max Act: 4.4325. Min Act: -0.0000

Data Index: 1504374 (Python Code)

Max Activating Token Index: 30

Text #3

Max Range: 4.7428. Min Range: -4.7428

Max Act: 4.4011. Min Act: -0.0000

Data Index: 1508041 (Python Code)

Max Activating Token Index: 907

Text #4

Max Range: 4.7428. Min Range: -4.7428

Max Act: 4.5868. Min Act: -0.0000

Data Index: 1425695 (Python Code)

Max Activating Token Index: 991

Text #5

Max Range: 4.7428. Min Range: -4.7428

Max Act: 4.4431. Min Act: -0.0000

Data Index: 897962 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 4.7428. Min Range: -4.7428

Max Act: 4.4171. Min Act: -0.0000

Data Index: 1616434 (Python Code)

Max Activating Token Index: 52

Text #7

Max Range: 4.7428. Min Range: -4.7428

Max Act: 4.0419. Min Act: -0.0000

Data Index: 1200855 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 4.7428. Min Range: -4.7428

Max Act: 4.0639. Min Act: -0.0000

Data Index: 1522335 (Python Code)

Max Activating Token Index: 743

Text #9

Max Range: 4.7428. Min Range: -4.7428

Max Act: 3.7290. Min Act: -0.0000

Data Index: 1646080 (Python Code)

Max Activating Token Index: 237

Text #10

Max Range: 4.7428. Min Range: -4.7428

Max Act: 3.7898. Min Act: -0.0000

Data Index: 455994 (C4 (Web Text))

Max Activating Token Index: 940

Text #11

Max Range: 4.7428. Min Range: -4.7428

Max Act: 4.0573. Min Act: -0.0000

Data Index: 881661 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 4.7428. Min Range: -4.7428

Max Act: 3.7957. Min Act: -0.0000

Data Index: 1508373 (Python Code)

Max Activating Token Index: 5

Text #13

Max Range: 4.7428. Min Range: -4.7428

Max Act: 3.5634. Min Act: -0.0000

Data Index: 1395951 (Python Code)

Max Activating Token Index: 963

Text #14

Max Range: 4.7428. Min Range: -4.7428

Max Act: 3.5139. Min Act: -0.0000

Data Index: 1494273 (Python Code)

Max Activating Token Index: 607

Text #15

Max Range: 4.7428. Min Range: -4.7428

Max Act: 3.5012. Min Act: -0.0000

Data Index: 1584640 (Python Code)

Max Activating Token Index: 869

Text #16

Max Range: 4.7428. Min Range: -4.7428

Max Act: 3.3517. Min Act: -0.0000

Data Index: 1251426 (C4 (Web Text))

Max Activating Token Index: 899

Text #17

Max Range: 4.7428. Min Range: -4.7428

Max Act: 3.4195. Min Act: -0.0000

Data Index: 1624213 (Python Code)

Max Activating Token Index: 639

Text #18

Max Range: 4.7428. Min Range: -4.7428

Max Act: 3.2864. Min Act: -0.0000

Data Index: 1366282 (Python Code)

Max Activating Token Index: 597

Text #19

Max Range: 4.7428. Min Range: -4.7428

Max Act: 3.4101. Min Act: -0.0000

Data Index: 1476697 (Python Code)

Max Activating Token Index: 644