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

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

Neuron 2333 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4730. Min Range: -5.4730

Max Act: 5.4730. Min Act: -0.0000

Data Index: 1484171 (Python Code)

Max Activating Token Index: 211

Text #1

Max Range: 5.4730. Min Range: -5.4730

Max Act: 5.2265. Min Act: -0.0000

Data Index: 1580970 (Python Code)

Max Activating Token Index: 52

Text #2

Max Range: 5.4730. Min Range: -5.4730

Max Act: 4.8099. Min Act: -0.0000

Data Index: 1483709 (Python Code)

Max Activating Token Index: 275

Text #3

Max Range: 5.4730. Min Range: -5.4730

Max Act: 5.0027. Min Act: -0.0000

Data Index: 250277 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 5.4730. Min Range: -5.4730

Max Act: 4.6457. Min Act: -0.0000

Data Index: 103336 (C4 (Web Text))

Max Activating Token Index: 582

Text #5

Max Range: 5.4730. Min Range: -5.4730

Max Act: 4.9289. Min Act: -0.0000

Data Index: 1391445 (Python Code)

Max Activating Token Index: 312

Text #6

Max Range: 5.4730. Min Range: -5.4730

Max Act: 4.7335. Min Act: -0.0000

Data Index: 687611 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 5.4730. Min Range: -5.4730

Max Act: 4.7261. Min Act: -0.0000

Data Index: 1614851 (Python Code)

Max Activating Token Index: 871

Text #8

Max Range: 5.4730. Min Range: -5.4730

Max Act: 4.7366. Min Act: -0.0000

Data Index: 327728 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 5.4730. Min Range: -5.4730

Max Act: 4.5190. Min Act: -0.0000

Data Index: 373379 (C4 (Web Text))

Max Activating Token Index: 295

Text #10

Max Range: 5.4730. Min Range: -5.4730

Max Act: 4.4606. Min Act: -0.0000

Data Index: 1433373 (Python Code)

Max Activating Token Index: 5

Text #11

Max Range: 5.4730. Min Range: -5.4730

Max Act: 4.4590. Min Act: -0.0000

Data Index: 1656464 (Python Code)

Max Activating Token Index: 85

Text #12

Max Range: 5.4730. Min Range: -5.4730

Max Act: 4.6312. Min Act: -0.0000

Data Index: 1610125 (Python Code)

Max Activating Token Index: 591

Text #13

Max Range: 5.4730. Min Range: -5.4730

Max Act: 4.4232. Min Act: -0.0000

Data Index: 954847 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 5.4730. Min Range: -5.4730

Max Act: 4.5895. Min Act: -0.0000

Data Index: 1560186 (Python Code)

Max Activating Token Index: 160

Text #15

Max Range: 5.4730. Min Range: -5.4730

Max Act: 4.5932. Min Act: -0.0000

Data Index: 1421792 (Python Code)

Max Activating Token Index: 431

Text #16

Max Range: 5.4730. Min Range: -5.4730

Max Act: 4.5436. Min Act: -0.0000

Data Index: 1527088 (Python Code)

Max Activating Token Index: 945

Text #17

Max Range: 5.4730. Min Range: -5.4730

Max Act: 4.5654. Min Act: -0.0000

Data Index: 1559764 (Python Code)

Max Activating Token Index: 7

Text #18

Max Range: 5.4730. Min Range: -5.4730

Max Act: 4.3926. Min Act: -0.0000

Data Index: 1063186 (C4 (Web Text))

Max Activating Token Index: 268

Text #19

Max Range: 5.4730. Min Range: -5.4730

Max Act: 4.0915. Min Act: -0.0000

Data Index: 1590483 (Python Code)

Max Activating Token Index: 734