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

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

Neuron 4244 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: 0.6062. Min Range: -0.6062

Max Act: 0.6062. Min Act: -0.0000

Data Index: 944913 (C4 (Web Text))

Max Activating Token Index: 362

Text #1

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.5394. Min Act: -0.0000

Data Index: 863136 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.5827. Min Act: -0.0000

Data Index: 216286 (C4 (Web Text))

Max Activating Token Index: 642

Text #3

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4921. Min Act: 0.0000

Data Index: 1042965 (C4 (Web Text))

Max Activating Token Index: 812

Text #4

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4981. Min Act: -0.0000

Data Index: 1082055 (C4 (Web Text))

Max Activating Token Index: 621

Text #5

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4600. Min Act: -0.0000

Data Index: 93413 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4651. Min Act: -0.0000

Data Index: 864667 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4446. Min Act: -0.0000

Data Index: 896455 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4213. Min Act: 0.0000

Data Index: 155624 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4464. Min Act: -0.0000

Data Index: 433447 (C4 (Web Text))

Max Activating Token Index: 408

Text #10

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4132. Min Act: -0.0000

Data Index: 1613989 (Python Code)

Max Activating Token Index: 785

Text #11

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4150. Min Act: -0.0000

Data Index: 1230362 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4077. Min Act: -0.0000

Data Index: 127773 (C4 (Web Text))

Max Activating Token Index: 359

Text #13

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4058. Min Act: -0.0000

Data Index: 631583 (C4 (Web Text))

Max Activating Token Index: 676

Text #14

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4055. Min Act: 0.0000

Data Index: 1295250 (C4 (Web Text))

Max Activating Token Index: 620

Text #15

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4305. Min Act: -0.0000

Data Index: 1649630 (Python Code)

Max Activating Token Index: 664

Text #16

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4106. Min Act: -0.0000

Data Index: 63589 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4126. Min Act: -0.0000

Data Index: 1036665 (C4 (Web Text))

Max Activating Token Index: 857

Text #18

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.3984. Min Act: -0.0000

Data Index: 1054446 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.3913. Min Act: -0.0000

Data Index: 307130 (C4 (Web Text))

Max Activating Token Index: 988