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

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

Neuron 4540 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.8366. Min Act: -0.0000

Data Index: 1371881 (Python Code)

Max Activating Token Index: 976

Text #1

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.9137. Min Act: -0.0000

Data Index: 1564515 (Python Code)

Max Activating Token Index: 931

Text #2

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.7338. Min Act: -0.0000

Data Index: 1411367 (Python Code)

Max Activating Token Index: 374

Text #3

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.7183. Min Act: -0.0000

Data Index: 1504150 (Python Code)

Max Activating Token Index: 593

Text #4

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.6763. Min Act: -0.0000

Data Index: 1596170 (Python Code)

Max Activating Token Index: 440

Text #5

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.6462. Min Act: -0.0000

Data Index: 1456136 (Python Code)

Max Activating Token Index: 521

Text #6

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.6347. Min Act: -0.0000

Data Index: 1439520 (Python Code)

Max Activating Token Index: 481

Text #7

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.6766. Min Act: -0.0000

Data Index: 1376843 (Python Code)

Max Activating Token Index: 546

Text #8

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.6317. Min Act: -0.0000

Data Index: 1528110 (Python Code)

Max Activating Token Index: 279

Text #9

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.6289. Min Act: -0.0000

Data Index: 1486064 (Python Code)

Max Activating Token Index: 795

Text #10

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.6300. Min Act: -0.0000

Data Index: 1435343 (Python Code)

Max Activating Token Index: 146

Text #11

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.6665. Min Act: -0.0000

Data Index: 1398291 (Python Code)

Max Activating Token Index: 555

Text #12

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.5808. Min Act: -0.0000

Data Index: 1585100 (Python Code)

Max Activating Token Index: 560

Text #13

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.6044. Min Act: -0.0000

Data Index: 1483210 (Python Code)

Max Activating Token Index: 344

Text #14

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.5760. Min Act: -0.0000

Data Index: 1604306 (Python Code)

Max Activating Token Index: 698

Text #15

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.5583. Min Act: -0.0000

Data Index: 1473303 (Python Code)

Max Activating Token Index: 150

Text #16

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.5955. Min Act: -0.0000

Data Index: 1565499 (Python Code)

Max Activating Token Index: 535

Text #17

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.5805. Min Act: -0.0000

Data Index: 1457362 (Python Code)

Max Activating Token Index: 799

Text #18

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.5406. Min Act: -0.0000

Data Index: 1403749 (Python Code)

Max Activating Token Index: 218

Text #19

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.5731. Min Act: -0.0000

Data Index: 1654481 (Python Code)

Max Activating Token Index: 264