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

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

Neuron 2358 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5439. Min Range: -2.5439

Max Act: 2.5439. Min Act: -0.0000

Data Index: 1479793 (Python Code)

Max Activating Token Index: 481

Text #1

Max Range: 2.5439. Min Range: -2.5439

Max Act: 2.4517. Min Act: -0.0000

Data Index: 1455787 (Python Code)

Max Activating Token Index: 377

Text #2

Max Range: 2.5439. Min Range: -2.5439

Max Act: 2.2431. Min Act: -0.0000

Data Index: 1371967 (Python Code)

Max Activating Token Index: 602

Text #3

Max Range: 2.5439. Min Range: -2.5439

Max Act: 2.0733. Min Act: -0.0000

Data Index: 1480359 (Python Code)

Max Activating Token Index: 920

Text #4

Max Range: 2.5439. Min Range: -2.5439

Max Act: 2.0009. Min Act: -0.0000

Data Index: 1629286 (Python Code)

Max Activating Token Index: 1009

Text #5

Max Range: 2.5439. Min Range: -2.5439

Max Act: 2.1003. Min Act: -0.0000

Data Index: 1465214 (Python Code)

Max Activating Token Index: 373

Text #6

Max Range: 2.5439. Min Range: -2.5439

Max Act: 2.0864. Min Act: -0.0000

Data Index: 1643655 (Python Code)

Max Activating Token Index: 911

Text #7

Max Range: 2.5439. Min Range: -2.5439

Max Act: 2.0017. Min Act: -0.0000

Data Index: 1387991 (Python Code)

Max Activating Token Index: 117

Text #8

Max Range: 2.5439. Min Range: -2.5439

Max Act: 1.9176. Min Act: -0.0000

Data Index: 1387162 (Python Code)

Max Activating Token Index: 986

Text #9

Max Range: 2.5439. Min Range: -2.5439

Max Act: 1.9897. Min Act: -0.0000

Data Index: 1567416 (Python Code)

Max Activating Token Index: 63

Text #10

Max Range: 2.5439. Min Range: -2.5439

Max Act: 1.9321. Min Act: -0.0000

Data Index: 1381678 (Python Code)

Max Activating Token Index: 664

Text #11

Max Range: 2.5439. Min Range: -2.5439

Max Act: 1.9053. Min Act: -0.0000

Data Index: 1640054 (Python Code)

Max Activating Token Index: 101

Text #12

Max Range: 2.5439. Min Range: -2.5439

Max Act: 1.8875. Min Act: -0.0000

Data Index: 1651637 (Python Code)

Max Activating Token Index: 362

Text #13

Max Range: 2.5439. Min Range: -2.5439

Max Act: 1.7625. Min Act: -0.0000

Data Index: 1497910 (Python Code)

Max Activating Token Index: 204

Text #14

Max Range: 2.5439. Min Range: -2.5439

Max Act: 1.8410. Min Act: -0.0000

Data Index: 1597265 (Python Code)

Max Activating Token Index: 634

Text #15

Max Range: 2.5439. Min Range: -2.5439

Max Act: 1.8180. Min Act: -0.0000

Data Index: 1596313 (Python Code)

Max Activating Token Index: 179

Text #16

Max Range: 2.5439. Min Range: -2.5439

Max Act: 1.6978. Min Act: -0.0000

Data Index: 1410614 (Python Code)

Max Activating Token Index: 244

Text #17

Max Range: 2.5439. Min Range: -2.5439

Max Act: 2.0125. Min Act: -0.0000

Data Index: 1490626 (Python Code)

Max Activating Token Index: 350

Text #18

Max Range: 2.5439. Min Range: -2.5439

Max Act: 1.7916. Min Act: -0.0000

Data Index: 1618761 (Python Code)

Max Activating Token Index: 933

Text #19

Max Range: 2.5439. Min Range: -2.5439

Max Act: 1.7788. Min Act: -0.0000

Data Index: 1383923 (Python Code)

Max Activating Token Index: 626