Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1573 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0149. Min Act: -0.0006

Data Index: 420177 (C4 (Web Text))

Max Activating Token Index: 599

Text #1

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0159. Min Act: -0.0006

Data Index: 838871 (C4 (Web Text))

Max Activating Token Index: 296

Text #2

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0144. Min Act: -0.0006

Data Index: 1252137 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0140. Min Act: -0.0006

Data Index: 627768 (C4 (Web Text))

Max Activating Token Index: 937

Text #4

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0140. Min Act: -0.0006

Data Index: 1320976 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0155. Min Act: -0.0006

Data Index: 291986 (C4 (Web Text))

Max Activating Token Index: 100

Text #6

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0151. Min Act: -0.0006

Data Index: 1141794 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0138. Min Act: -0.0006

Data Index: 855001 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0129. Min Act: -0.0006

Data Index: 557815 (C4 (Web Text))

Max Activating Token Index: 527

Text #9

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0154. Min Act: -0.0006

Data Index: 112089 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0141. Min Act: -0.0006

Data Index: 183697 (C4 (Web Text))

Max Activating Token Index: 408

Text #11

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0140. Min Act: -0.0006

Data Index: 763882 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0136. Min Act: -0.0006

Data Index: 661661 (C4 (Web Text))

Max Activating Token Index: 886

Text #13

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0139. Min Act: -0.0006

Data Index: 174267 (C4 (Web Text))

Max Activating Token Index: 59

Text #14

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0122. Min Act: -0.0006

Data Index: 814133 (C4 (Web Text))

Max Activating Token Index: 780

Text #15

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0138. Min Act: -0.0006

Data Index: 718908 (C4 (Web Text))

Max Activating Token Index: 93

Text #16

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0147. Min Act: -0.0006

Data Index: 848936 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0141. Min Act: -0.0006

Data Index: 59013 (C4 (Web Text))

Max Activating Token Index: 208

Text #18

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0133. Min Act: -0.0006

Data Index: 1251156 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0133. Min Act: -0.0006

Data Index: 828557 (C4 (Web Text))

Max Activating Token Index: 289