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

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

Neuron 1545 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: 7.5626. Min Range: -7.5626

Max Act: 7.5626. Min Act: -0.0000

Data Index: 1556012 (Python Code)

Max Activating Token Index: 404

Text #1

Max Range: 7.5626. Min Range: -7.5626

Max Act: 4.1585. Min Act: -0.0000

Data Index: 1593350 (Python Code)

Max Activating Token Index: 956

Text #2

Max Range: 7.5626. Min Range: -7.5626

Max Act: 3.7212. Min Act: -0.0000

Data Index: 1449647 (Python Code)

Max Activating Token Index: 498

Text #3

Max Range: 7.5626. Min Range: -7.5626

Max Act: 3.8939. Min Act: -0.0000

Data Index: 1620448 (Python Code)

Max Activating Token Index: 449

Text #4

Max Range: 7.5626. Min Range: -7.5626

Max Act: 3.7949. Min Act: -0.0000

Data Index: 1470467 (Python Code)

Max Activating Token Index: 258

Text #5

Max Range: 7.5626. Min Range: -7.5626

Max Act: 2.8971. Min Act: -0.0000

Data Index: 1394003 (Python Code)

Max Activating Token Index: 357

Text #6

Max Range: 7.5626. Min Range: -7.5626

Max Act: 2.6533. Min Act: -0.0000

Data Index: 1391867 (Python Code)

Max Activating Token Index: 574

Text #7

Max Range: 7.5626. Min Range: -7.5626

Max Act: 2.3775. Min Act: -0.0000

Data Index: 1368012 (Python Code)

Max Activating Token Index: 494

Text #8

Max Range: 7.5626. Min Range: -7.5626

Max Act: 2.1034. Min Act: -0.0000

Data Index: 1550687 (Python Code)

Max Activating Token Index: 305

Text #9

Max Range: 7.5626. Min Range: -7.5626

Max Act: 2.1462. Min Act: -0.0000

Data Index: 1375421 (Python Code)

Max Activating Token Index: 200

Text #10

Max Range: 7.5626. Min Range: -7.5626

Max Act: 2.0029. Min Act: -0.0000

Data Index: 1464520 (Python Code)

Max Activating Token Index: 227

Text #11

Max Range: 7.5626. Min Range: -7.5626

Max Act: 1.8361. Min Act: -0.0000

Data Index: 1597107 (Python Code)

Max Activating Token Index: 148

Text #12

Max Range: 7.5626. Min Range: -7.5626

Max Act: 1.9330. Min Act: -0.0000

Data Index: 1435770 (Python Code)

Max Activating Token Index: 468

Text #13

Max Range: 7.5626. Min Range: -7.5626

Max Act: 1.7178. Min Act: -0.0000

Data Index: 1653641 (Python Code)

Max Activating Token Index: 931

Text #14

Max Range: 7.5626. Min Range: -7.5626

Max Act: 1.6124. Min Act: -0.0000

Data Index: 791860 (C4 (Web Text))

Max Activating Token Index: 634

Text #15

Max Range: 7.5626. Min Range: -7.5626

Max Act: 1.6850. Min Act: -0.0000

Data Index: 1648335 (Python Code)

Max Activating Token Index: 912

Text #16

Max Range: 7.5626. Min Range: -7.5626

Max Act: 1.6940. Min Act: -0.0000

Data Index: 1411728 (Python Code)

Max Activating Token Index: 443

Text #17

Max Range: 7.5626. Min Range: -7.5626

Max Act: 1.3454. Min Act: -0.0000

Data Index: 1409000 (Python Code)

Max Activating Token Index: 49

Text #18

Max Range: 7.5626. Min Range: -7.5626

Max Act: 1.4790. Min Act: -0.0000

Data Index: 606867 (C4 (Web Text))

Max Activating Token Index: 926

Text #19

Max Range: 7.5626. Min Range: -7.5626

Max Act: 1.3717. Min Act: -0.0000

Data Index: 408634 (C4 (Web Text))

Max Activating Token Index: 862