Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4317 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0144. Min Act: -0.0002

Data Index: 402537 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0141. Min Act: -0.0002

Data Index: 469967 (C4 (Web Text))

Max Activating Token Index: 305

Text #2

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0140. Min Act: -0.0002

Data Index: 473022 (C4 (Web Text))

Max Activating Token Index: 648

Text #3

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0136. Min Act: -0.0002

Data Index: 811553 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0139. Min Act: -0.0002

Data Index: 738814 (C4 (Web Text))

Max Activating Token Index: 397

Text #5

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0139. Min Act: -0.0002

Data Index: 1128881 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0137. Min Act: -0.0002

Data Index: 1070065 (C4 (Web Text))

Max Activating Token Index: 973

Text #7

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0137. Min Act: -0.0002

Data Index: 585688 (C4 (Web Text))

Max Activating Token Index: 161

Text #8

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0137. Min Act: -0.0002

Data Index: 41117 (C4 (Web Text))

Max Activating Token Index: 125

Text #9

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0134. Min Act: -0.0002

Data Index: 813107 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0136. Min Act: -0.0002

Data Index: 948366 (C4 (Web Text))

Max Activating Token Index: 132

Text #11

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0133. Min Act: -0.0002

Data Index: 597755 (C4 (Web Text))

Max Activating Token Index: 527

Text #12

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0133. Min Act: -0.0002

Data Index: 1138505 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0133. Min Act: -0.0002

Data Index: 1029328 (C4 (Web Text))

Max Activating Token Index: 479

Text #14

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0132. Min Act: -0.0002

Data Index: 1110125 (C4 (Web Text))

Max Activating Token Index: 230

Text #15

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0132. Min Act: -0.0002

Data Index: 757024 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0131. Min Act: -0.0002

Data Index: 1077807 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0131. Min Act: -0.0002

Data Index: 487912 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0130. Min Act: -0.0002

Data Index: 749583 (C4 (Web Text))

Max Activating Token Index: 279

Text #19

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0129. Min Act: -0.0002

Data Index: 534891 (C4 (Web Text))

Max Activating Token Index: 277