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

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

Neuron 4502 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0208. Min Act: -0.0002

Data Index: 1381382 (Python Code)

Max Activating Token Index: 811

Text #1

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0187. Min Act: -0.0003

Data Index: 435548 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0172. Min Act: -0.0003

Data Index: 435039 (C4 (Web Text))

Max Activating Token Index: 234

Text #3

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0163. Min Act: -0.0003

Data Index: 1644240 (Python Code)

Max Activating Token Index: 941

Text #4

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0161. Min Act: -0.0003

Data Index: 943117 (C4 (Web Text))

Max Activating Token Index: 564

Text #5

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0163. Min Act: -0.0003

Data Index: 1364904 (Python Code)

Max Activating Token Index: 704

Text #6

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0164. Min Act: -0.0003

Data Index: 431797 (C4 (Web Text))

Max Activating Token Index: 420

Text #7

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0156. Min Act: -0.0002

Data Index: 1257893 (C4 (Web Text))

Max Activating Token Index: 722

Text #8

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0161. Min Act: -0.0003

Data Index: 956255 (C4 (Web Text))

Max Activating Token Index: 962

Text #9

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0147. Min Act: -0.0002

Data Index: 813361 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0151. Min Act: -0.0003

Data Index: 215328 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0155. Min Act: -0.0003

Data Index: 520227 (C4 (Web Text))

Max Activating Token Index: 949

Text #12

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0153. Min Act: -0.0002

Data Index: 551364 (C4 (Web Text))

Max Activating Token Index: 551

Text #13

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0144. Min Act: -0.0003

Data Index: 861090 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0151. Min Act: -0.0003

Data Index: 227892 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0146. Min Act: -0.0002

Data Index: 493721 (C4 (Web Text))

Max Activating Token Index: 390

Text #16

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0138. Min Act: -0.0003

Data Index: 1332977 (C4 (Web Text))

Max Activating Token Index: 99

Text #17

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0138. Min Act: -0.0003

Data Index: 1490525 (Python Code)

Max Activating Token Index: 109

Text #18

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0143. Min Act: -0.0002

Data Index: 1037678 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0143. Min Act: -0.0002

Data Index: 1519250 (Python Code)

Max Activating Token Index: 846