Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4668 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.6010. Min Act: -0.0002

Data Index: 1466058 (Python Code)

Max Activating Token Index: 784

Text #1

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.6349. Min Act: -0.0002

Data Index: 1458083 (Python Code)

Max Activating Token Index: 4

Text #2

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.5497. Min Act: -0.0002

Data Index: 1650523 (Python Code)

Max Activating Token Index: 721

Text #3

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.5720. Min Act: -0.0002

Data Index: 1525706 (Python Code)

Max Activating Token Index: 294

Text #4

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.5879. Min Act: -0.0002

Data Index: 1364991 (Python Code)

Max Activating Token Index: 257

Text #5

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.4880. Min Act: -0.0002

Data Index: 1609939 (Python Code)

Max Activating Token Index: 564

Text #6

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.5350. Min Act: -0.0002

Data Index: 1636938 (Python Code)

Max Activating Token Index: 8

Text #7

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.6106. Min Act: -0.0002

Data Index: 1550663 (Python Code)

Max Activating Token Index: 721

Text #8

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.4563. Min Act: -0.0002

Data Index: 1621073 (Python Code)

Max Activating Token Index: 861

Text #9

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.5238. Min Act: -0.0002

Data Index: 1620225 (Python Code)

Max Activating Token Index: 7

Text #10

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.4888. Min Act: -0.0002

Data Index: 1400729 (Python Code)

Max Activating Token Index: 264

Text #11

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.5294. Min Act: -0.0002

Data Index: 1618570 (Python Code)

Max Activating Token Index: 770

Text #12

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.5286. Min Act: -0.0002

Data Index: 1628696 (Python Code)

Max Activating Token Index: 734

Text #13

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.4427. Min Act: -0.0002

Data Index: 1507184 (Python Code)

Max Activating Token Index: 677

Text #14

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.5434. Min Act: -0.0002

Data Index: 1576992 (Python Code)

Max Activating Token Index: 10

Text #15

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.5969. Min Act: -0.0002

Data Index: 1603011 (Python Code)

Max Activating Token Index: 8

Text #16

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.5780. Min Act: -0.0002

Data Index: 1576939 (Python Code)

Max Activating Token Index: 731

Text #17

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.4796. Min Act: -0.0002

Data Index: 1617293 (Python Code)

Max Activating Token Index: 772

Text #18

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.5563. Min Act: -0.0002

Data Index: 1558388 (Python Code)

Max Activating Token Index: 6

Text #19

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.5576. Min Act: -0.0002

Data Index: 1534565 (Python Code)

Max Activating Token Index: 902