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

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

Neuron 2618 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.9215. Min Act: -0.0000

Data Index: 102694 (C4 (Web Text))

Max Activating Token Index: 631

Text #1

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.7412. Min Act: -0.0000

Data Index: 1045780 (C4 (Web Text))

Max Activating Token Index: 949

Text #2

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.6801. Min Act: -0.0000

Data Index: 85536 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.8159. Min Act: -0.0000

Data Index: 77997 (C4 (Web Text))

Max Activating Token Index: 840

Text #4

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.6093. Min Act: -0.0000

Data Index: 351571 (C4 (Web Text))

Max Activating Token Index: 257

Text #5

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.5736. Min Act: -0.0000

Data Index: 688844 (C4 (Web Text))

Max Activating Token Index: 406

Text #6

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.5043. Min Act: -0.0000

Data Index: 476857 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.5689. Min Act: -0.0000

Data Index: 702973 (C4 (Web Text))

Max Activating Token Index: 3

Text #8

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.5522. Min Act: -0.0000

Data Index: 1505159 (Python Code)

Max Activating Token Index: 234

Text #9

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.5265. Min Act: -0.0000

Data Index: 1573780 (Python Code)

Max Activating Token Index: 838

Text #10

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.4987. Min Act: -0.0000

Data Index: 1101950 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.5375. Min Act: -0.0000

Data Index: 297813 (C4 (Web Text))

Max Activating Token Index: 110

Text #12

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.4868. Min Act: -0.0000

Data Index: 1490580 (Python Code)

Max Activating Token Index: 719

Text #13

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.4678. Min Act: -0.0000

Data Index: 1467731 (Python Code)

Max Activating Token Index: 99

Text #14

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.5313. Min Act: -0.0000

Data Index: 1398325 (Python Code)

Max Activating Token Index: 703

Text #15

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.4768. Min Act: -0.0000

Data Index: 1485377 (Python Code)

Max Activating Token Index: 334

Text #16

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.4611. Min Act: -0.0000

Data Index: 453103 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.4836. Min Act: -0.0000

Data Index: 1534923 (Python Code)

Max Activating Token Index: 128

Text #18

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.4924. Min Act: -0.0000

Data Index: 1323092 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.4781. Min Act: -0.0000

Data Index: 1569787 (Python Code)

Max Activating Token Index: 764