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

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

Neuron 1715 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0164. Min Act: -0.0005

Data Index: 98034 (C4 (Web Text))

Max Activating Token Index: 509

Text #1

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0163. Min Act: -0.0005

Data Index: 1328783 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0161. Min Act: -0.0006

Data Index: 876706 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0152. Min Act: -0.0006

Data Index: 1140887 (C4 (Web Text))

Max Activating Token Index: 765

Text #4

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0152. Min Act: -0.0005

Data Index: 1177895 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0155. Min Act: -0.0006

Data Index: 549793 (C4 (Web Text))

Max Activating Token Index: 455

Text #6

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0152. Min Act: -0.0005

Data Index: 153123 (C4 (Web Text))

Max Activating Token Index: 761

Text #7

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0151. Min Act: -0.0005

Data Index: 712081 (C4 (Web Text))

Max Activating Token Index: 246

Text #8

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0151. Min Act: -0.0005

Data Index: 455301 (C4 (Web Text))

Max Activating Token Index: 346

Text #9

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0151. Min Act: -0.0006

Data Index: 47968 (C4 (Web Text))

Max Activating Token Index: 263

Text #10

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0150. Min Act: -0.0005

Data Index: 1317928 (C4 (Web Text))

Max Activating Token Index: 262

Text #11

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0146. Min Act: -0.0005

Data Index: 94534 (C4 (Web Text))

Max Activating Token Index: 952

Text #12

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0149. Min Act: -0.0005

Data Index: 886775 (C4 (Web Text))

Max Activating Token Index: 746

Text #13

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0147. Min Act: -0.0005

Data Index: 653101 (C4 (Web Text))

Max Activating Token Index: 942

Text #14

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0146. Min Act: -0.0005

Data Index: 1268075 (C4 (Web Text))

Max Activating Token Index: 511

Text #15

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0144. Min Act: -0.0006

Data Index: 1199469 (C4 (Web Text))

Max Activating Token Index: 6

Text #16

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0146. Min Act: -0.0005

Data Index: 1009813 (C4 (Web Text))

Max Activating Token Index: 557

Text #17

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0143. Min Act: -0.0005

Data Index: 1056607 (C4 (Web Text))

Max Activating Token Index: 555

Text #18

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0142. Min Act: -0.0005

Data Index: 722414 (C4 (Web Text))

Max Activating Token Index: 231

Text #19

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0142. Min Act: -0.0006

Data Index: 1342152 (C4 (Web Text))

Max Activating Token Index: 529