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

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

Neuron 4642 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: 0.9065. Min Range: -0.9065

Max Act: 0.9065. Min Act: -0.0000

Data Index: 1447284 (Python Code)

Max Activating Token Index: 67

Text #1

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.8463. Min Act: -0.0000

Data Index: 1409620 (Python Code)

Max Activating Token Index: 386

Text #2

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.8949. Min Act: -0.0000

Data Index: 1410594 (Python Code)

Max Activating Token Index: 734

Text #3

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.7620. Min Act: -0.0000

Data Index: 1430842 (Python Code)

Max Activating Token Index: 992

Text #4

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.8062. Min Act: -0.0000

Data Index: 1488007 (Python Code)

Max Activating Token Index: 365

Text #5

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.7983. Min Act: -0.0000

Data Index: 1575090 (Python Code)

Max Activating Token Index: 914

Text #6

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.7241. Min Act: -0.0000

Data Index: 1492489 (Python Code)

Max Activating Token Index: 122

Text #7

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.7035. Min Act: -0.0000

Data Index: 1578234 (Python Code)

Max Activating Token Index: 517

Text #8

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.6747. Min Act: -0.0000

Data Index: 1518926 (Python Code)

Max Activating Token Index: 109

Text #9

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.6495. Min Act: -0.0000

Data Index: 1448752 (Python Code)

Max Activating Token Index: 81

Text #10

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.6759. Min Act: -0.0000

Data Index: 1378068 (Python Code)

Max Activating Token Index: 63

Text #11

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.6157. Min Act: -0.0000

Data Index: 1414234 (Python Code)

Max Activating Token Index: 677

Text #12

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.5915. Min Act: -0.0000

Data Index: 1503660 (Python Code)

Max Activating Token Index: 619

Text #13

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.5975. Min Act: -0.0000

Data Index: 1585573 (Python Code)

Max Activating Token Index: 54

Text #14

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.5918. Min Act: -0.0000

Data Index: 1516659 (Python Code)

Max Activating Token Index: 61

Text #15

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.5101. Min Act: -0.0000

Data Index: 1529100 (Python Code)

Max Activating Token Index: 263

Text #16

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.5305. Min Act: -0.0000

Data Index: 1395708 (Python Code)

Max Activating Token Index: 998

Text #17

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.5463. Min Act: -0.0000

Data Index: 1366545 (Python Code)

Max Activating Token Index: 800

Text #18

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.5353. Min Act: -0.0000

Data Index: 1360073 (Python Code)

Max Activating Token Index: 348

Text #19

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.5459. Min Act: -0.0000

Data Index: 1530052 (Python Code)

Max Activating Token Index: 9