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

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

Neuron 3177 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.3059. Min Act: -0.0001

Data Index: 58936 (C4 (Web Text))

Max Activating Token Index: 258

Text #1

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2732. Min Act: -0.0001

Data Index: 433339 (C4 (Web Text))

Max Activating Token Index: 485

Text #2

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2836. Min Act: -0.0001

Data Index: 1170396 (C4 (Web Text))

Max Activating Token Index: 329

Text #3

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2360. Min Act: -0.0001

Data Index: 457866 (C4 (Web Text))

Max Activating Token Index: 747

Text #4

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2543. Min Act: -0.0001

Data Index: 112862 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2498. Min Act: -0.0001

Data Index: 187636 (C4 (Web Text))

Max Activating Token Index: 365

Text #6

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2432. Min Act: -0.0001

Data Index: 227328 (C4 (Web Text))

Max Activating Token Index: 603

Text #7

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2304. Min Act: -0.0001

Data Index: 1310854 (C4 (Web Text))

Max Activating Token Index: 971

Text #8

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2196. Min Act: -0.0001

Data Index: 535244 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2472. Min Act: -0.0001

Data Index: 794563 (C4 (Web Text))

Max Activating Token Index: 600

Text #10

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2369. Min Act: -0.0001

Data Index: 735797 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2191. Min Act: -0.0001

Data Index: 150270 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2089. Min Act: -0.0001

Data Index: 630161 (C4 (Web Text))

Max Activating Token Index: 699

Text #13

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2014. Min Act: -0.0001

Data Index: 221036 (C4 (Web Text))

Max Activating Token Index: 181

Text #14

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2052. Min Act: -0.0001

Data Index: 1158708 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2025. Min Act: -0.0001

Data Index: 1176277 (C4 (Web Text))

Max Activating Token Index: 1016

Text #16

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2004. Min Act: -0.0001

Data Index: 280892 (C4 (Web Text))

Max Activating Token Index: 467

Text #17

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.1930. Min Act: -0.0001

Data Index: 996016 (C4 (Web Text))

Max Activating Token Index: 549

Text #18

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2050. Min Act: -0.0001

Data Index: 757122 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2104. Min Act: -0.0001

Data Index: 775062 (C4 (Web Text))

Max Activating Token Index: 449