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

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

Neuron 5599 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: 1.1414. Min Range: -1.1414

Max Act: 1.1414. Min Act: -0.0000

Data Index: 1501403 (Python Code)

Max Activating Token Index: 496

Text #1

Max Range: 1.1414. Min Range: -1.1414

Max Act: 1.1393. Min Act: -0.0000

Data Index: 1436990 (Python Code)

Max Activating Token Index: 661

Text #2

Max Range: 1.1414. Min Range: -1.1414

Max Act: 0.9468. Min Act: -0.0000

Data Index: 1516406 (Python Code)

Max Activating Token Index: 390

Text #3

Max Range: 1.1414. Min Range: -1.1414

Max Act: 1.0542. Min Act: -0.0000

Data Index: 1495931 (Python Code)

Max Activating Token Index: 294

Text #4

Max Range: 1.1414. Min Range: -1.1414

Max Act: 1.0199. Min Act: -0.0001

Data Index: 1597744 (Python Code)

Max Activating Token Index: 193

Text #5

Max Range: 1.1414. Min Range: -1.1414

Max Act: 0.9852. Min Act: -0.0001

Data Index: 1652758 (Python Code)

Max Activating Token Index: 696

Text #6

Max Range: 1.1414. Min Range: -1.1414

Max Act: 0.9835. Min Act: -0.0000

Data Index: 1617598 (Python Code)

Max Activating Token Index: 327

Text #7

Max Range: 1.1414. Min Range: -1.1414

Max Act: 0.9497. Min Act: -0.0000

Data Index: 1396021 (Python Code)

Max Activating Token Index: 688

Text #8

Max Range: 1.1414. Min Range: -1.1414

Max Act: 0.9471. Min Act: -0.0000

Data Index: 1366227 (Python Code)

Max Activating Token Index: 34

Text #9

Max Range: 1.1414. Min Range: -1.1414

Max Act: 0.9735. Min Act: -0.0000

Data Index: 1650693 (Python Code)

Max Activating Token Index: 272

Text #10

Max Range: 1.1414. Min Range: -1.1414

Max Act: 0.8612. Min Act: -0.0001

Data Index: 1428456 (Python Code)

Max Activating Token Index: 275

Text #11

Max Range: 1.1414. Min Range: -1.1414

Max Act: 0.8724. Min Act: -0.0000

Data Index: 1506997 (Python Code)

Max Activating Token Index: 7

Text #12

Max Range: 1.1414. Min Range: -1.1414

Max Act: 0.8630. Min Act: -0.0001

Data Index: 1368553 (Python Code)

Max Activating Token Index: 466

Text #13

Max Range: 1.1414. Min Range: -1.1414

Max Act: 0.8568. Min Act: -0.0001

Data Index: 1548559 (Python Code)

Max Activating Token Index: 1012

Text #14

Max Range: 1.1414. Min Range: -1.1414

Max Act: 0.8329. Min Act: -0.0000

Data Index: 1390530 (Python Code)

Max Activating Token Index: 594

Text #15

Max Range: 1.1414. Min Range: -1.1414

Max Act: 0.8155. Min Act: -0.0001

Data Index: 1533590 (Python Code)

Max Activating Token Index: 517

Text #16

Max Range: 1.1414. Min Range: -1.1414

Max Act: 0.8294. Min Act: -0.0000

Data Index: 1580899 (Python Code)

Max Activating Token Index: 352

Text #17

Max Range: 1.1414. Min Range: -1.1414

Max Act: 0.7621. Min Act: -0.0001

Data Index: 1425261 (Python Code)

Max Activating Token Index: 151

Text #18

Max Range: 1.1414. Min Range: -1.1414

Max Act: 0.8352. Min Act: -0.0001

Data Index: 1421414 (Python Code)

Max Activating Token Index: 616

Text #19

Max Range: 1.1414. Min Range: -1.1414

Max Act: 0.7240. Min Act: -0.0000

Data Index: 1460543 (Python Code)

Max Activating Token Index: 137