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

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

Neuron 2529 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0186. Min Act: -0.0004

Data Index: 642642 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0154. Min Act: -0.0004

Data Index: 640854 (C4 (Web Text))

Max Activating Token Index: 308

Text #2

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0153. Min Act: -0.0004

Data Index: 771021 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0158. Min Act: -0.0004

Data Index: 216520 (C4 (Web Text))

Max Activating Token Index: 810

Text #4

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0161. Min Act: -0.0004

Data Index: 37510 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0149. Min Act: -0.0004

Data Index: 1318944 (C4 (Web Text))

Max Activating Token Index: 988

Text #6

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0149. Min Act: -0.0004

Data Index: 792526 (C4 (Web Text))

Max Activating Token Index: 691

Text #7

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0152. Min Act: -0.0004

Data Index: 739608 (C4 (Web Text))

Max Activating Token Index: 846

Text #8

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0155. Min Act: -0.0004

Data Index: 137692 (C4 (Web Text))

Max Activating Token Index: 963

Text #9

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0157. Min Act: -0.0004

Data Index: 640720 (C4 (Web Text))

Max Activating Token Index: 630

Text #10

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0137. Min Act: -0.0004

Data Index: 984483 (C4 (Web Text))

Max Activating Token Index: 581

Text #11

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0148. Min Act: -0.0004

Data Index: 164756 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0147. Min Act: -0.0004

Data Index: 877387 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0137. Min Act: -0.0004

Data Index: 727958 (C4 (Web Text))

Max Activating Token Index: 656

Text #14

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0151. Min Act: -0.0004

Data Index: 766376 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0142. Min Act: -0.0004

Data Index: 1111867 (C4 (Web Text))

Max Activating Token Index: 588

Text #16

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0125. Min Act: -0.0004

Data Index: 1091099 (C4 (Web Text))

Max Activating Token Index: 290

Text #17

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0129. Min Act: -0.0004

Data Index: 126854 (C4 (Web Text))

Max Activating Token Index: 437

Text #18

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0126. Min Act: -0.0004

Data Index: 347679 (C4 (Web Text))

Max Activating Token Index: 863

Text #19

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0131. Min Act: -0.0004

Data Index: 986486 (C4 (Web Text))

Max Activating Token Index: 657