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

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

Neuron 844 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: 0.0599. Min Range: -0.0599

Max Act: 0.0599. Min Act: -0.0002

Data Index: 1481322 (Python Code)

Max Activating Token Index: 17

Text #1

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0473. Min Act: -0.0002

Data Index: 1492638 (Python Code)

Max Activating Token Index: 412

Text #2

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0429. Min Act: -0.0002

Data Index: 1470265 (Python Code)

Max Activating Token Index: 34

Text #3

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0464. Min Act: -0.0002

Data Index: 1653915 (Python Code)

Max Activating Token Index: 865

Text #4

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0410. Min Act: -0.0002

Data Index: 1555767 (Python Code)

Max Activating Token Index: 14

Text #5

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0412. Min Act: -0.0002

Data Index: 1570295 (Python Code)

Max Activating Token Index: 83

Text #6

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0422. Min Act: -0.0002

Data Index: 1411790 (Python Code)

Max Activating Token Index: 35

Text #7

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0423. Min Act: -0.0002

Data Index: 1448903 (Python Code)

Max Activating Token Index: 247

Text #8

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0417. Min Act: -0.0002

Data Index: 1617151 (Python Code)

Max Activating Token Index: 437

Text #9

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0374. Min Act: -0.0002

Data Index: 1553880 (Python Code)

Max Activating Token Index: 13

Text #10

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0389. Min Act: -0.0002

Data Index: 1424147 (Python Code)

Max Activating Token Index: 31

Text #11

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0398. Min Act: -0.0002

Data Index: 1439351 (Python Code)

Max Activating Token Index: 236

Text #12

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0389. Min Act: -0.0002

Data Index: 1615026 (Python Code)

Max Activating Token Index: 162

Text #13

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0369. Min Act: -0.0002

Data Index: 1510069 (Python Code)

Max Activating Token Index: 32

Text #14

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0402. Min Act: -0.0002

Data Index: 1603617 (Python Code)

Max Activating Token Index: 223

Text #15

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0414. Min Act: -0.0002

Data Index: 1525871 (Python Code)

Max Activating Token Index: 159

Text #16

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0391. Min Act: -0.0002

Data Index: 1585748 (Python Code)

Max Activating Token Index: 403

Text #17

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0380. Min Act: -0.0002

Data Index: 1534414 (Python Code)

Max Activating Token Index: 9

Text #18

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0404. Min Act: -0.0002

Data Index: 1608046 (Python Code)

Max Activating Token Index: 813

Text #19

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0372. Min Act: -0.0002

Data Index: 1510882 (Python Code)

Max Activating Token Index: 93