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

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

Neuron 4441 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8972. Min Range: -0.8972

Max Act: 0.8495. Min Act: -0.0000

Data Index: 1433347 (Python Code)

Max Activating Token Index: 175

Text #1

Max Range: 0.8972. Min Range: -0.8972

Max Act: 0.8890. Min Act: -0.0000

Data Index: 1394496 (Python Code)

Max Activating Token Index: 86

Text #2

Max Range: 0.8972. Min Range: -0.8972

Max Act: 0.8721. Min Act: -0.0000

Data Index: 1518459 (Python Code)

Max Activating Token Index: 236

Text #3

Max Range: 0.8972. Min Range: -0.8972

Max Act: 0.8802. Min Act: -0.0000

Data Index: 1640062 (Python Code)

Max Activating Token Index: 207

Text #4

Max Range: 0.8972. Min Range: -0.8972

Max Act: 0.8972. Min Act: -0.0000

Data Index: 1564664 (Python Code)

Max Activating Token Index: 291

Text #5

Max Range: 0.8972. Min Range: -0.8972

Max Act: 0.7755. Min Act: -0.0000

Data Index: 1371362 (Python Code)

Max Activating Token Index: 740

Text #6

Max Range: 0.8972. Min Range: -0.8972

Max Act: 0.7906. Min Act: -0.0000

Data Index: 1507002 (Python Code)

Max Activating Token Index: 873

Text #7

Max Range: 0.8972. Min Range: -0.8972

Max Act: 0.7774. Min Act: -0.0000

Data Index: 1473606 (Python Code)

Max Activating Token Index: 28

Text #8

Max Range: 0.8972. Min Range: -0.8972

Max Act: 0.7625. Min Act: -0.0000

Data Index: 1497028 (Python Code)

Max Activating Token Index: 306

Text #9

Max Range: 0.8972. Min Range: -0.8972

Max Act: 0.8018. Min Act: -0.0000

Data Index: 1428038 (Python Code)

Max Activating Token Index: 1011

Text #10

Max Range: 0.8972. Min Range: -0.8972

Max Act: 0.7216. Min Act: -0.0000

Data Index: 1377429 (Python Code)

Max Activating Token Index: 39

Text #11

Max Range: 0.8972. Min Range: -0.8972

Max Act: 0.7985. Min Act: -0.0000

Data Index: 1528212 (Python Code)

Max Activating Token Index: 940

Text #12

Max Range: 0.8972. Min Range: -0.8972

Max Act: 0.7362. Min Act: -0.0000

Data Index: 1463760 (Python Code)

Max Activating Token Index: 969

Text #13

Max Range: 0.8972. Min Range: -0.8972

Max Act: 0.6966. Min Act: -0.0000

Data Index: 1556376 (Python Code)

Max Activating Token Index: 622

Text #14

Max Range: 0.8972. Min Range: -0.8972

Max Act: 0.6826. Min Act: -0.0000

Data Index: 1386356 (Python Code)

Max Activating Token Index: 801

Text #15

Max Range: 0.8972. Min Range: -0.8972

Max Act: 0.6910. Min Act: -0.0000

Data Index: 1375165 (Python Code)

Max Activating Token Index: 476

Text #16

Max Range: 0.8972. Min Range: -0.8972

Max Act: 0.6349. Min Act: -0.0000

Data Index: 1486374 (Python Code)

Max Activating Token Index: 322

Text #17

Max Range: 0.8972. Min Range: -0.8972

Max Act: 0.5948. Min Act: -0.0000

Data Index: 1582565 (Python Code)

Max Activating Token Index: 190

Text #18

Max Range: 0.8972. Min Range: -0.8972

Max Act: 0.5418. Min Act: -0.0000

Data Index: 1622332 (Python Code)

Max Activating Token Index: 372

Text #19

Max Range: 0.8972. Min Range: -0.8972

Max Act: 0.6048. Min Act: -0.0000

Data Index: 1591798 (Python Code)

Max Activating Token Index: 264