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

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

Neuron 140 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3750. Min Range: -2.3750

Max Act: 2.3750. Min Act: -0.0000

Data Index: 1581879 (Python Code)

Max Activating Token Index: 363

Text #1

Max Range: 2.3750. Min Range: -2.3750

Max Act: 2.3745. Min Act: -0.0000

Data Index: 1378274 (Python Code)

Max Activating Token Index: 1001

Text #2

Max Range: 2.3750. Min Range: -2.3750

Max Act: 2.2518. Min Act: -0.0000

Data Index: 1504863 (Python Code)

Max Activating Token Index: 308

Text #3

Max Range: 2.3750. Min Range: -2.3750

Max Act: 1.9033. Min Act: -0.0000

Data Index: 1412996 (Python Code)

Max Activating Token Index: 808

Text #4

Max Range: 2.3750. Min Range: -2.3750

Max Act: 1.8723. Min Act: -0.0000

Data Index: 1473649 (Python Code)

Max Activating Token Index: 583

Text #5

Max Range: 2.3750. Min Range: -2.3750

Max Act: 1.5625. Min Act: -0.0000

Data Index: 1555412 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 2.3750. Min Range: -2.3750

Max Act: 1.7256. Min Act: -0.0000

Data Index: 1371875 (Python Code)

Max Activating Token Index: 437

Text #7

Max Range: 2.3750. Min Range: -2.3750

Max Act: 1.7013. Min Act: -0.0000

Data Index: 1617687 (Python Code)

Max Activating Token Index: 264

Text #8

Max Range: 2.3750. Min Range: -2.3750

Max Act: 1.6063. Min Act: -0.0000

Data Index: 1531231 (Python Code)

Max Activating Token Index: 306

Text #9

Max Range: 2.3750. Min Range: -2.3750

Max Act: 1.6647. Min Act: -0.0000

Data Index: 1608971 (Python Code)

Max Activating Token Index: 807

Text #10

Max Range: 2.3750. Min Range: -2.3750

Max Act: 1.4710. Min Act: -0.0000

Data Index: 1520709 (Python Code)

Max Activating Token Index: 301

Text #11

Max Range: 2.3750. Min Range: -2.3750

Max Act: 1.6113. Min Act: -0.0000

Data Index: 1488258 (Python Code)

Max Activating Token Index: 136

Text #12

Max Range: 2.3750. Min Range: -2.3750

Max Act: 1.7849. Min Act: -0.0000

Data Index: 1414112 (Python Code)

Max Activating Token Index: 878

Text #13

Max Range: 2.3750. Min Range: -2.3750

Max Act: 1.5748. Min Act: -0.0000

Data Index: 1570336 (Python Code)

Max Activating Token Index: 293

Text #14

Max Range: 2.3750. Min Range: -2.3750

Max Act: 1.5610. Min Act: -0.0000

Data Index: 1576302 (Python Code)

Max Activating Token Index: 834

Text #15

Max Range: 2.3750. Min Range: -2.3750

Max Act: 1.4403. Min Act: -0.0000

Data Index: 1598016 (Python Code)

Max Activating Token Index: 182

Text #16

Max Range: 2.3750. Min Range: -2.3750

Max Act: 1.4893. Min Act: -0.0000

Data Index: 1518053 (Python Code)

Max Activating Token Index: 461

Text #17

Max Range: 2.3750. Min Range: -2.3750

Max Act: 1.4844. Min Act: -0.0000

Data Index: 1540348 (Python Code)

Max Activating Token Index: 291

Text #18

Max Range: 2.3750. Min Range: -2.3750

Max Act: 1.4789. Min Act: -0.0000

Data Index: 1554603 (Python Code)

Max Activating Token Index: 423

Text #19

Max Range: 2.3750. Min Range: -2.3750

Max Act: 1.4785. Min Act: -0.0000

Data Index: 1429710 (Python Code)

Max Activating Token Index: 975