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

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

Neuron 1242 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: 6.8908. Min Range: -6.8908

Max Act: 6.8908. Min Act: -0.0000

Data Index: 1648238 (Python Code)

Max Activating Token Index: 492

Text #1

Max Range: 6.8908. Min Range: -6.8908

Max Act: 6.6562. Min Act: -0.0000

Data Index: 1464984 (Python Code)

Max Activating Token Index: 50

Text #2

Max Range: 6.8908. Min Range: -6.8908

Max Act: 6.3837. Min Act: -0.0000

Data Index: 1493995 (Python Code)

Max Activating Token Index: 127

Text #3

Max Range: 6.8908. Min Range: -6.8908

Max Act: 5.5880. Min Act: -0.0000

Data Index: 1623549 (Python Code)

Max Activating Token Index: 354

Text #4

Max Range: 6.8908. Min Range: -6.8908

Max Act: 5.4290. Min Act: -0.0000

Data Index: 1525297 (Python Code)

Max Activating Token Index: 348

Text #5

Max Range: 6.8908. Min Range: -6.8908

Max Act: 5.2531. Min Act: -0.0000

Data Index: 1604474 (Python Code)

Max Activating Token Index: 4

Text #6

Max Range: 6.8908. Min Range: -6.8908

Max Act: 5.3693. Min Act: -0.0000

Data Index: 1499648 (Python Code)

Max Activating Token Index: 654

Text #7

Max Range: 6.8908. Min Range: -6.8908

Max Act: 5.1720. Min Act: -0.0000

Data Index: 1422598 (Python Code)

Max Activating Token Index: 951

Text #8

Max Range: 6.8908. Min Range: -6.8908

Max Act: 5.2999. Min Act: -0.0000

Data Index: 1643159 (Python Code)

Max Activating Token Index: 3

Text #9

Max Range: 6.8908. Min Range: -6.8908

Max Act: 5.1310. Min Act: -0.0000

Data Index: 1469531 (Python Code)

Max Activating Token Index: 690

Text #10

Max Range: 6.8908. Min Range: -6.8908

Max Act: 5.2586. Min Act: -0.0000

Data Index: 1498684 (Python Code)

Max Activating Token Index: 1013

Text #11

Max Range: 6.8908. Min Range: -6.8908

Max Act: 5.0155. Min Act: -0.0000

Data Index: 1557221 (Python Code)

Max Activating Token Index: 449

Text #12

Max Range: 6.8908. Min Range: -6.8908

Max Act: 5.1137. Min Act: -0.0000

Data Index: 1391842 (Python Code)

Max Activating Token Index: 287

Text #13

Max Range: 6.8908. Min Range: -6.8908

Max Act: 4.7914. Min Act: -0.0000

Data Index: 1467284 (Python Code)

Max Activating Token Index: 1003

Text #14

Max Range: 6.8908. Min Range: -6.8908

Max Act: 4.8869. Min Act: -0.0000

Data Index: 1514394 (Python Code)

Max Activating Token Index: 106

Text #15

Max Range: 6.8908. Min Range: -6.8908

Max Act: 4.4792. Min Act: -0.0000

Data Index: 1409751 (Python Code)

Max Activating Token Index: 17

Text #16

Max Range: 6.8908. Min Range: -6.8908

Max Act: 4.3239. Min Act: -0.0000

Data Index: 1564643 (Python Code)

Max Activating Token Index: 340

Text #17

Max Range: 6.8908. Min Range: -6.8908

Max Act: 4.6131. Min Act: -0.0000

Data Index: 1539764 (Python Code)

Max Activating Token Index: 346

Text #18

Max Range: 6.8908. Min Range: -6.8908

Max Act: 4.4036. Min Act: -0.0000

Data Index: 1432509 (Python Code)

Max Activating Token Index: 328

Text #19

Max Range: 6.8908. Min Range: -6.8908

Max Act: 4.5957. Min Act: -0.0000

Data Index: 1444838 (Python Code)

Max Activating Token Index: 559