Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2128 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2012. Min Range: -0.2012

Max Act: 0.2012. Min Act: -0.0000

Data Index: 444155 (C4 (Web Text))

Max Activating Token Index: 419

Text #1

Max Range: 0.2012. Min Range: -0.2012

Max Act: 0.1789. Min Act: -0.0000

Data Index: 779238 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 0.2012. Min Range: -0.2012

Max Act: 0.1406. Min Act: -0.0000

Data Index: 1123597 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 0.2012. Min Range: -0.2012

Max Act: 0.1387. Min Act: -0.0000

Data Index: 872186 (C4 (Web Text))

Max Activating Token Index: 443

Text #4

Max Range: 0.2012. Min Range: -0.2012

Max Act: 0.1469. Min Act: -0.0000

Data Index: 941244 (C4 (Web Text))

Max Activating Token Index: 571

Text #5

Max Range: 0.2012. Min Range: -0.2012

Max Act: 0.1302. Min Act: -0.0000

Data Index: 912451 (C4 (Web Text))

Max Activating Token Index: 558

Text #6

Max Range: 0.2012. Min Range: -0.2012

Max Act: 0.1365. Min Act: -0.0000

Data Index: 485944 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 0.2012. Min Range: -0.2012

Max Act: 0.1279. Min Act: -0.0000

Data Index: 248912 (C4 (Web Text))

Max Activating Token Index: 712

Text #8

Max Range: 0.2012. Min Range: -0.2012

Max Act: 0.1187. Min Act: -0.0000

Data Index: 876060 (C4 (Web Text))

Max Activating Token Index: 976

Text #9

Max Range: 0.2012. Min Range: -0.2012

Max Act: 0.1181. Min Act: -0.0000

Data Index: 1005576 (C4 (Web Text))

Max Activating Token Index: 624

Text #10

Max Range: 0.2012. Min Range: -0.2012

Max Act: 0.1097. Min Act: -0.0000

Data Index: 922609 (C4 (Web Text))

Max Activating Token Index: 551

Text #11

Max Range: 0.2012. Min Range: -0.2012

Max Act: 0.1101. Min Act: -0.0000

Data Index: 318879 (C4 (Web Text))

Max Activating Token Index: 889

Text #12

Max Range: 0.2012. Min Range: -0.2012

Max Act: 0.1091. Min Act: -0.0000

Data Index: 1357125 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 0.2012. Min Range: -0.2012

Max Act: 0.1104. Min Act: -0.0000

Data Index: 137948 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 0.2012. Min Range: -0.2012

Max Act: 0.1050. Min Act: -0.0000

Data Index: 238869 (C4 (Web Text))

Max Activating Token Index: 589

Text #15

Max Range: 0.2012. Min Range: -0.2012

Max Act: 0.1046. Min Act: -0.0000

Data Index: 182961 (C4 (Web Text))

Max Activating Token Index: 451

Text #16

Max Range: 0.2012. Min Range: -0.2012

Max Act: 0.1061. Min Act: -0.0000

Data Index: 733603 (C4 (Web Text))

Max Activating Token Index: 679

Text #17

Max Range: 0.2012. Min Range: -0.2012

Max Act: 0.0986. Min Act: -0.0000

Data Index: 360857 (C4 (Web Text))

Max Activating Token Index: 591

Text #18

Max Range: 0.2012. Min Range: -0.2012

Max Act: 0.0970. Min Act: -0.0000

Data Index: 1291520 (C4 (Web Text))

Max Activating Token Index: 901

Text #19

Max Range: 0.2012. Min Range: -0.2012

Max Act: 0.1028. Min Act: -0.0000

Data Index: 939805 (C4 (Web Text))

Max Activating Token Index: 135