Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 795 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2859. Min Act: -0.0001

Data Index: 1358334 (C4 (Web Text))

Max Activating Token Index: 376

Text #1

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2374. Min Act: -0.0001

Data Index: 37496 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2251. Min Act: -0.0001

Data Index: 196753 (C4 (Web Text))

Max Activating Token Index: 995

Text #3

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2284. Min Act: -0.0001

Data Index: 618570 (C4 (Web Text))

Max Activating Token Index: 261

Text #4

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2260. Min Act: -0.0002

Data Index: 556506 (C4 (Web Text))

Max Activating Token Index: 519

Text #5

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2199. Min Act: -0.0001

Data Index: 593398 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2191. Min Act: -0.0002

Data Index: 198286 (C4 (Web Text))

Max Activating Token Index: 872

Text #7

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2092. Min Act: -0.0001

Data Index: 508646 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2148. Min Act: -0.0002

Data Index: 879851 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2174. Min Act: -0.0001

Data Index: 1118982 (C4 (Web Text))

Max Activating Token Index: 621

Text #10

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2056. Min Act: -0.0001

Data Index: 509498 (C4 (Web Text))

Max Activating Token Index: 891

Text #11

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2079. Min Act: -0.0002

Data Index: 1342178 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2047. Min Act: -0.0002

Data Index: 1279486 (C4 (Web Text))

Max Activating Token Index: 566

Text #13

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2055. Min Act: -0.0002

Data Index: 699449 (C4 (Web Text))

Max Activating Token Index: 483

Text #14

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2088. Min Act: -0.0001

Data Index: 47346 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2011. Min Act: -0.0002

Data Index: 1076085 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2101. Min Act: -0.0001

Data Index: 582963 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2004. Min Act: -0.0002

Data Index: 749949 (C4 (Web Text))

Max Activating Token Index: 668

Text #18

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2016. Min Act: -0.0001

Data Index: 621376 (C4 (Web Text))

Max Activating Token Index: 288

Text #19

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2075. Min Act: -0.0001

Data Index: 306237 (C4 (Web Text))

Max Activating Token Index: 457