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

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

Neuron 3169 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0199. Min Range: -2.0199

Max Act: 2.0199. Min Act: -0.0000

Data Index: 1532856 (Python Code)

Max Activating Token Index: 210

Text #1

Max Range: 2.0199. Min Range: -2.0199

Max Act: 1.4841. Min Act: -0.0000

Data Index: 1582151 (Python Code)

Max Activating Token Index: 542

Text #2

Max Range: 2.0199. Min Range: -2.0199

Max Act: 1.4097. Min Act: 0.0000

Data Index: 1645045 (Python Code)

Max Activating Token Index: 279

Text #3

Max Range: 2.0199. Min Range: -2.0199

Max Act: 1.1998. Min Act: -0.0000

Data Index: 1527968 (Python Code)

Max Activating Token Index: 68

Text #4

Max Range: 2.0199. Min Range: -2.0199

Max Act: 1.2002. Min Act: -0.0000

Data Index: 1632894 (Python Code)

Max Activating Token Index: 156

Text #5

Max Range: 2.0199. Min Range: -2.0199

Max Act: 1.2583. Min Act: -0.0000

Data Index: 1360787 (Python Code)

Max Activating Token Index: 607

Text #6

Max Range: 2.0199. Min Range: -2.0199

Max Act: 1.2619. Min Act: -0.0000

Data Index: 1577540 (Python Code)

Max Activating Token Index: 801

Text #7

Max Range: 2.0199. Min Range: -2.0199

Max Act: 1.2404. Min Act: -0.0000

Data Index: 1591111 (Python Code)

Max Activating Token Index: 662

Text #8

Max Range: 2.0199. Min Range: -2.0199

Max Act: 1.2222. Min Act: -0.0000

Data Index: 1549907 (Python Code)

Max Activating Token Index: 36

Text #9

Max Range: 2.0199. Min Range: -2.0199

Max Act: 1.2853. Min Act: -0.0000

Data Index: 1564127 (Python Code)

Max Activating Token Index: 1004

Text #10

Max Range: 2.0199. Min Range: -2.0199

Max Act: 1.2027. Min Act: -0.0000

Data Index: 1546203 (Python Code)

Max Activating Token Index: 456

Text #11

Max Range: 2.0199. Min Range: -2.0199

Max Act: 1.1256. Min Act: -0.0000

Data Index: 1617912 (Python Code)

Max Activating Token Index: 328

Text #12

Max Range: 2.0199. Min Range: -2.0199

Max Act: 1.0987. Min Act: -0.0000

Data Index: 1365139 (Python Code)

Max Activating Token Index: 47

Text #13

Max Range: 2.0199. Min Range: -2.0199

Max Act: 1.1510. Min Act: -0.0000

Data Index: 1372160 (Python Code)

Max Activating Token Index: 19

Text #14

Max Range: 2.0199. Min Range: -2.0199

Max Act: 1.1245. Min Act: 0.0000

Data Index: 1452326 (Python Code)

Max Activating Token Index: 248

Text #15

Max Range: 2.0199. Min Range: -2.0199

Max Act: 1.0427. Min Act: 0.0000

Data Index: 1560754 (Python Code)

Max Activating Token Index: 888

Text #16

Max Range: 2.0199. Min Range: -2.0199

Max Act: 0.9657. Min Act: -0.0000

Data Index: 1439265 (Python Code)

Max Activating Token Index: 424

Text #17

Max Range: 2.0199. Min Range: -2.0199

Max Act: 1.0874. Min Act: -0.0000

Data Index: 1601492 (Python Code)

Max Activating Token Index: 480

Text #18

Max Range: 2.0199. Min Range: -2.0199

Max Act: 1.2061. Min Act: -0.0000

Data Index: 1439995 (Python Code)

Max Activating Token Index: 886

Text #19

Max Range: 2.0199. Min Range: -2.0199

Max Act: 1.0685. Min Act: -0.0000

Data Index: 1514655 (Python Code)

Max Activating Token Index: 816