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

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

Neuron 5167 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5076. Min Range: -3.5076

Max Act: 3.5076. Min Act: -0.0000

Data Index: 43198 (C4 (Web Text))

Max Activating Token Index: 1004

Text #1

Max Range: 3.5076. Min Range: -3.5076

Max Act: 3.2116. Min Act: -0.0000

Data Index: 855083 (C4 (Web Text))

Max Activating Token Index: 1012

Text #2

Max Range: 3.5076. Min Range: -3.5076

Max Act: 2.9992. Min Act: -0.0000

Data Index: 463477 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 3.5076. Min Range: -3.5076

Max Act: 3.0101. Min Act: -0.0000

Data Index: 1018669 (C4 (Web Text))

Max Activating Token Index: 709

Text #4

Max Range: 3.5076. Min Range: -3.5076

Max Act: 2.9860. Min Act: -0.0000

Data Index: 1529784 (Python Code)

Max Activating Token Index: 86

Text #5

Max Range: 3.5076. Min Range: -3.5076

Max Act: 2.8012. Min Act: 0.0000

Data Index: 599212 (C4 (Web Text))

Max Activating Token Index: 528

Text #6

Max Range: 3.5076. Min Range: -3.5076

Max Act: 2.6347. Min Act: 0.0000

Data Index: 205411 (C4 (Web Text))

Max Activating Token Index: 967

Text #7

Max Range: 3.5076. Min Range: -3.5076

Max Act: 2.7147. Min Act: -0.0000

Data Index: 1286019 (C4 (Web Text))

Max Activating Token Index: 751

Text #8

Max Range: 3.5076. Min Range: -3.5076

Max Act: 2.6918. Min Act: -0.0000

Data Index: 853376 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 3.5076. Min Range: -3.5076

Max Act: 2.5386. Min Act: 0.0000

Data Index: 126055 (C4 (Web Text))

Max Activating Token Index: 944

Text #10

Max Range: 3.5076. Min Range: -3.5076

Max Act: 2.4228. Min Act: -0.0000

Data Index: 83053 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 3.5076. Min Range: -3.5076

Max Act: 2.3354. Min Act: -0.0000

Data Index: 1086575 (C4 (Web Text))

Max Activating Token Index: 518

Text #12

Max Range: 3.5076. Min Range: -3.5076

Max Act: 2.4080. Min Act: 0.0000

Data Index: 392083 (C4 (Web Text))

Max Activating Token Index: 930

Text #13

Max Range: 3.5076. Min Range: -3.5076

Max Act: 2.5067. Min Act: -0.0000

Data Index: 1415233 (Python Code)

Max Activating Token Index: 452

Text #14

Max Range: 3.5076. Min Range: -3.5076

Max Act: 2.4105. Min Act: -0.0000

Data Index: 1192140 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 3.5076. Min Range: -3.5076

Max Act: 2.4478. Min Act: -0.0000

Data Index: 1410830 (Python Code)

Max Activating Token Index: 225

Text #16

Max Range: 3.5076. Min Range: -3.5076

Max Act: 2.3609. Min Act: 0.0000

Data Index: 1028801 (C4 (Web Text))

Max Activating Token Index: 1020

Text #17

Max Range: 3.5076. Min Range: -3.5076

Max Act: 2.2616. Min Act: 0.0000

Data Index: 736671 (C4 (Web Text))

Max Activating Token Index: 495

Text #18

Max Range: 3.5076. Min Range: -3.5076

Max Act: 2.3304. Min Act: -0.0000

Data Index: 1453897 (Python Code)

Max Activating Token Index: 80

Text #19

Max Range: 3.5076. Min Range: -3.5076

Max Act: 2.3041. Min Act: -0.0000

Data Index: 112240 (C4 (Web Text))

Max Activating Token Index: 83