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

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

Neuron 5532 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.5832. Min Act: -0.0000

Data Index: 1386626 (Python Code)

Max Activating Token Index: 235

Text #1

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.5096. Min Act: -0.0000

Data Index: 1479586 (Python Code)

Max Activating Token Index: 239

Text #2

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.4955. Min Act: 0.0000

Data Index: 1500667 (Python Code)

Max Activating Token Index: 692

Text #3

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.5240. Min Act: 0.0000

Data Index: 1410787 (Python Code)

Max Activating Token Index: 37

Text #4

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.4748. Min Act: -0.0000

Data Index: 1486391 (Python Code)

Max Activating Token Index: 107

Text #5

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.4659. Min Act: -0.0000

Data Index: 1640490 (Python Code)

Max Activating Token Index: 206

Text #6

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.4601. Min Act: -0.0000

Data Index: 1576470 (Python Code)

Max Activating Token Index: 349

Text #7

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.4357. Min Act: -0.0000

Data Index: 1370812 (Python Code)

Max Activating Token Index: 50

Text #8

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.4514. Min Act: -0.0000

Data Index: 1628584 (Python Code)

Max Activating Token Index: 584

Text #9

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.4456. Min Act: -0.0000

Data Index: 1502532 (Python Code)

Max Activating Token Index: 66

Text #10

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.4314. Min Act: -0.0000

Data Index: 1450609 (Python Code)

Max Activating Token Index: 141

Text #11

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.4490. Min Act: -0.0000

Data Index: 1371848 (Python Code)

Max Activating Token Index: 42

Text #12

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.4243. Min Act: -0.0000

Data Index: 1588724 (Python Code)

Max Activating Token Index: 190

Text #13

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.4380. Min Act: -0.0000

Data Index: 1448834 (Python Code)

Max Activating Token Index: 377

Text #14

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.3991. Min Act: -0.0000

Data Index: 1597906 (Python Code)

Max Activating Token Index: 96

Text #15

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.4124. Min Act: -0.0000

Data Index: 1420640 (Python Code)

Max Activating Token Index: 263

Text #16

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.3942. Min Act: -0.0000

Data Index: 1495473 (Python Code)

Max Activating Token Index: 115

Text #17

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.4041. Min Act: -0.0000

Data Index: 1507647 (Python Code)

Max Activating Token Index: 653

Text #18

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.3899. Min Act: -0.0000

Data Index: 1395177 (Python Code)

Max Activating Token Index: 567

Text #19

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.3911. Min Act: -0.0000

Data Index: 1529634 (Python Code)

Max Activating Token Index: 229