Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1455 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0180. Min Act: -0.0003

Data Index: 880636 (C4 (Web Text))

Max Activating Token Index: 348

Text #1

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0157. Min Act: -0.0003

Data Index: 794721 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0151. Min Act: -0.0003

Data Index: 313967 (C4 (Web Text))

Max Activating Token Index: 433

Text #3

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0153. Min Act: -0.0003

Data Index: 605573 (C4 (Web Text))

Max Activating Token Index: 134

Text #4

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0148. Min Act: -0.0003

Data Index: 427310 (C4 (Web Text))

Max Activating Token Index: 661

Text #5

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0147. Min Act: -0.0003

Data Index: 990678 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0150. Min Act: -0.0003

Data Index: 403954 (C4 (Web Text))

Max Activating Token Index: 769

Text #7

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0143. Min Act: -0.0003

Data Index: 1178832 (C4 (Web Text))

Max Activating Token Index: 816

Text #8

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0136. Min Act: -0.0003

Data Index: 869586 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0137. Min Act: -0.0003

Data Index: 469815 (C4 (Web Text))

Max Activating Token Index: 972

Text #10

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0136. Min Act: -0.0003

Data Index: 647049 (C4 (Web Text))

Max Activating Token Index: 387

Text #11

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0131. Min Act: -0.0003

Data Index: 1074484 (C4 (Web Text))

Max Activating Token Index: 234

Text #12

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0129. Min Act: -0.0003

Data Index: 657869 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0125. Min Act: -0.0003

Data Index: 227785 (C4 (Web Text))

Max Activating Token Index: 548

Text #14

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0132. Min Act: -0.0003

Data Index: 428318 (C4 (Web Text))

Max Activating Token Index: 472

Text #15

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0131. Min Act: -0.0003

Data Index: 564390 (C4 (Web Text))

Max Activating Token Index: 609

Text #16

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0127. Min Act: -0.0003

Data Index: 177109 (C4 (Web Text))

Max Activating Token Index: 582

Text #17

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0121. Min Act: -0.0003

Data Index: 1168947 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0126. Min Act: -0.0003

Data Index: 625801 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0137. Min Act: -0.0003

Data Index: 890526 (C4 (Web Text))

Max Activating Token Index: 654