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

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

Neuron 5 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: 0.7961. Min Range: -0.7961

Max Act: 0.7458. Min Act: -0.0000

Data Index: 1077526 (C4 (Web Text))

Max Activating Token Index: 912

Text #1

Max Range: 0.7961. Min Range: -0.7961

Max Act: 0.7961. Min Act: -0.0000

Data Index: 670599 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 0.7961. Min Range: -0.7961

Max Act: 0.5444. Min Act: -0.0000

Data Index: 868645 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 0.7961. Min Range: -0.7961

Max Act: 0.4676. Min Act: -0.0000

Data Index: 448157 (C4 (Web Text))

Max Activating Token Index: 53

Text #4

Max Range: 0.7961. Min Range: -0.7961

Max Act: 0.4340. Min Act: -0.0000

Data Index: 1273102 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 0.7961. Min Range: -0.7961

Max Act: 0.4284. Min Act: -0.0000

Data Index: 372295 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 0.7961. Min Range: -0.7961

Max Act: 0.3945. Min Act: -0.0000

Data Index: 812178 (C4 (Web Text))

Max Activating Token Index: 1006

Text #7

Max Range: 0.7961. Min Range: -0.7961

Max Act: 0.4098. Min Act: -0.0000

Data Index: 700357 (C4 (Web Text))

Max Activating Token Index: 371

Text #8

Max Range: 0.7961. Min Range: -0.7961

Max Act: 0.3968. Min Act: -0.0000

Data Index: 779872 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 0.7961. Min Range: -0.7961

Max Act: 0.3825. Min Act: -0.0000

Data Index: 123717 (C4 (Web Text))

Max Activating Token Index: 703

Text #10

Max Range: 0.7961. Min Range: -0.7961

Max Act: 0.4046. Min Act: -0.0000

Data Index: 927722 (C4 (Web Text))

Max Activating Token Index: 919

Text #11

Max Range: 0.7961. Min Range: -0.7961

Max Act: 0.3768. Min Act: -0.0000

Data Index: 215214 (C4 (Web Text))

Max Activating Token Index: 519

Text #12

Max Range: 0.7961. Min Range: -0.7961

Max Act: 0.3909. Min Act: -0.0000

Data Index: 694972 (C4 (Web Text))

Max Activating Token Index: 842

Text #13

Max Range: 0.7961. Min Range: -0.7961

Max Act: 0.3802. Min Act: -0.0000

Data Index: 1574408 (Python Code)

Max Activating Token Index: 1005

Text #14

Max Range: 0.7961. Min Range: -0.7961

Max Act: 0.3676. Min Act: -0.0000

Data Index: 243333 (C4 (Web Text))

Max Activating Token Index: 783

Text #15

Max Range: 0.7961. Min Range: -0.7961

Max Act: 0.3569. Min Act: -0.0000

Data Index: 1121843 (C4 (Web Text))

Max Activating Token Index: 923

Text #16

Max Range: 0.7961. Min Range: -0.7961

Max Act: 0.3744. Min Act: -0.0000

Data Index: 1073661 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 0.7961. Min Range: -0.7961

Max Act: 0.3840. Min Act: -0.0000

Data Index: 1419488 (Python Code)

Max Activating Token Index: 730

Text #18

Max Range: 0.7961. Min Range: -0.7961

Max Act: 0.3650. Min Act: -0.0000

Data Index: 1229658 (C4 (Web Text))

Max Activating Token Index: 1016

Text #19

Max Range: 0.7961. Min Range: -0.7961

Max Act: 0.3756. Min Act: -0.0000

Data Index: 904586 (C4 (Web Text))

Max Activating Token Index: 475