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

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

Neuron 5443 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.9004. Min Act: -0.0000

Data Index: 1471739 (Python Code)

Max Activating Token Index: 508

Text #1

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.8152. Min Act: -0.0000

Data Index: 1386663 (Python Code)

Max Activating Token Index: 104

Text #2

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.8087. Min Act: -0.0000

Data Index: 1650584 (Python Code)

Max Activating Token Index: 136

Text #3

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.7822. Min Act: -0.0000

Data Index: 1647734 (Python Code)

Max Activating Token Index: 642

Text #4

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.6968. Min Act: -0.0000

Data Index: 1597240 (Python Code)

Max Activating Token Index: 114

Text #5

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.7056. Min Act: -0.0000

Data Index: 1495561 (Python Code)

Max Activating Token Index: 107

Text #6

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.6818. Min Act: -0.0000

Data Index: 1416110 (Python Code)

Max Activating Token Index: 55

Text #7

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.6895. Min Act: -0.0000

Data Index: 1597948 (Python Code)

Max Activating Token Index: 973

Text #8

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.7108. Min Act: -0.0000

Data Index: 1480044 (Python Code)

Max Activating Token Index: 739

Text #9

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.6863. Min Act: -0.0000

Data Index: 1534549 (Python Code)

Max Activating Token Index: 297

Text #10

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.6984. Min Act: -0.0000

Data Index: 1566548 (Python Code)

Max Activating Token Index: 51

Text #11

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.6878. Min Act: -0.0000

Data Index: 1522571 (Python Code)

Max Activating Token Index: 138

Text #12

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.6768. Min Act: -0.0000

Data Index: 1549539 (Python Code)

Max Activating Token Index: 217

Text #13

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.6448. Min Act: -0.0000

Data Index: 1498490 (Python Code)

Max Activating Token Index: 927

Text #14

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.6125. Min Act: -0.0000

Data Index: 1655785 (Python Code)

Max Activating Token Index: 679

Text #15

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.6238. Min Act: -0.0000

Data Index: 1515902 (Python Code)

Max Activating Token Index: 85

Text #16

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.6030. Min Act: -0.0000

Data Index: 1493244 (Python Code)

Max Activating Token Index: 176

Text #17

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.6000. Min Act: -0.0000

Data Index: 1634675 (Python Code)

Max Activating Token Index: 115

Text #18

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.6151. Min Act: -0.0000

Data Index: 1585113 (Python Code)

Max Activating Token Index: 441

Text #19

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.6122. Min Act: -0.0000

Data Index: 1500935 (Python Code)

Max Activating Token Index: 652