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

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

Neuron 1478 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: 0.0165. Min Range: -0.0165

Max Act: 0.0165. Min Act: -0.0006

Data Index: 395074 (C4 (Web Text))

Max Activating Token Index: 163

Text #1

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0163. Min Act: -0.0006

Data Index: 1205475 (C4 (Web Text))

Max Activating Token Index: 502

Text #2

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0148. Min Act: -0.0006

Data Index: 833709 (C4 (Web Text))

Max Activating Token Index: 209

Text #3

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0150. Min Act: -0.0006

Data Index: 410861 (C4 (Web Text))

Max Activating Token Index: 103

Text #4

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0142. Min Act: -0.0006

Data Index: 557982 (C4 (Web Text))

Max Activating Token Index: 280

Text #5

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0147. Min Act: -0.0006

Data Index: 790000 (C4 (Web Text))

Max Activating Token Index: 627

Text #6

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0141. Min Act: -0.0006

Data Index: 130958 (C4 (Web Text))

Max Activating Token Index: 219

Text #7

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0136. Min Act: -0.0006

Data Index: 1044368 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0133. Min Act: -0.0006

Data Index: 247478 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0136. Min Act: -0.0006

Data Index: 716216 (C4 (Web Text))

Max Activating Token Index: 731

Text #10

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0125. Min Act: -0.0006

Data Index: 599273 (C4 (Web Text))

Max Activating Token Index: 710

Text #11

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0134. Min Act: -0.0006

Data Index: 1019786 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0139. Min Act: -0.0006

Data Index: 1285406 (C4 (Web Text))

Max Activating Token Index: 601

Text #13

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0133. Min Act: -0.0006

Data Index: 186961 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0130. Min Act: -0.0006

Data Index: 1016401 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0129. Min Act: -0.0006

Data Index: 1195747 (C4 (Web Text))

Max Activating Token Index: 229

Text #16

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0129. Min Act: -0.0006

Data Index: 547416 (C4 (Web Text))

Max Activating Token Index: 619

Text #17

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0126. Min Act: -0.0006

Data Index: 1355047 (C4 (Web Text))

Max Activating Token Index: 828

Text #18

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0131. Min Act: -0.0006

Data Index: 1138732 (C4 (Web Text))

Max Activating Token Index: 31

Text #19

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0129. Min Act: -0.0006

Data Index: 460109 (C4 (Web Text))

Max Activating Token Index: 629