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

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

Neuron 700 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0805. Min Range: -4.0805

Max Act: 3.8920. Min Act: -0.0000

Data Index: 1603476 (Python Code)

Max Activating Token Index: 457

Text #1

Max Range: 4.0805. Min Range: -4.0805

Max Act: 4.0805. Min Act: -0.0000

Data Index: 1561947 (Python Code)

Max Activating Token Index: 483

Text #2

Max Range: 4.0805. Min Range: -4.0805

Max Act: 3.0980. Min Act: -0.0000

Data Index: 27128 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 4.0805. Min Range: -4.0805

Max Act: 2.8914. Min Act: -0.0000

Data Index: 1032442 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 4.0805. Min Range: -4.0805

Max Act: 2.5767. Min Act: -0.0000

Data Index: 660839 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 4.0805. Min Range: -4.0805

Max Act: 2.6546. Min Act: -0.0000

Data Index: 113954 (C4 (Web Text))

Max Activating Token Index: 899

Text #6

Max Range: 4.0805. Min Range: -4.0805

Max Act: 2.6494. Min Act: -0.0000

Data Index: 80937 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 4.0805. Min Range: -4.0805

Max Act: 2.3705. Min Act: -0.0000

Data Index: 1059233 (C4 (Web Text))

Max Activating Token Index: 634

Text #8

Max Range: 4.0805. Min Range: -4.0805

Max Act: 2.6138. Min Act: -0.0000

Data Index: 1430706 (Python Code)

Max Activating Token Index: 815

Text #9

Max Range: 4.0805. Min Range: -4.0805

Max Act: 2.4699. Min Act: -0.0000

Data Index: 1332686 (C4 (Web Text))

Max Activating Token Index: 463

Text #10

Max Range: 4.0805. Min Range: -4.0805

Max Act: 2.4870. Min Act: -0.0000

Data Index: 188414 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 4.0805. Min Range: -4.0805

Max Act: 2.5805. Min Act: -0.0000

Data Index: 292915 (C4 (Web Text))

Max Activating Token Index: 542

Text #12

Max Range: 4.0805. Min Range: -4.0805

Max Act: 2.0076. Min Act: -0.0000

Data Index: 26421 (C4 (Web Text))

Max Activating Token Index: 645

Text #13

Max Range: 4.0805. Min Range: -4.0805

Max Act: 2.2303. Min Act: -0.0000

Data Index: 1466067 (Python Code)

Max Activating Token Index: 710

Text #14

Max Range: 4.0805. Min Range: -4.0805

Max Act: 2.5056. Min Act: -0.0000

Data Index: 161520 (C4 (Web Text))

Max Activating Token Index: 171

Text #15

Max Range: 4.0805. Min Range: -4.0805

Max Act: 2.0420. Min Act: -0.0000

Data Index: 432431 (C4 (Web Text))

Max Activating Token Index: 240

Text #16

Max Range: 4.0805. Min Range: -4.0805

Max Act: 2.2291. Min Act: -0.0000

Data Index: 460367 (C4 (Web Text))

Max Activating Token Index: 1020

Text #17

Max Range: 4.0805. Min Range: -4.0805

Max Act: 2.3436. Min Act: -0.0000

Data Index: 1332283 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 4.0805. Min Range: -4.0805

Max Act: 2.1032. Min Act: -0.0000

Data Index: 589763 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 4.0805. Min Range: -4.0805

Max Act: 2.2986. Min Act: -0.0000

Data Index: 400317 (C4 (Web Text))

Max Activating Token Index: 123