Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3354 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0201. Min Act: -0.0003

Data Index: 1272766 (C4 (Web Text))

Max Activating Token Index: 121

Text #1

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0177. Min Act: -0.0003

Data Index: 620865 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0157. Min Act: -0.0003

Data Index: 767426 (C4 (Web Text))

Max Activating Token Index: 350

Text #3

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0147. Min Act: -0.0003

Data Index: 831352 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0143. Min Act: -0.0003

Data Index: 131615 (C4 (Web Text))

Max Activating Token Index: 337

Text #5

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0138. Min Act: -0.0003

Data Index: 64953 (C4 (Web Text))

Max Activating Token Index: 961

Text #6

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0149. Min Act: -0.0003

Data Index: 132135 (C4 (Web Text))

Max Activating Token Index: 1020

Text #7

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0131. Min Act: -0.0003

Data Index: 26954 (C4 (Web Text))

Max Activating Token Index: 822

Text #8

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0140. Min Act: -0.0003

Data Index: 861365 (C4 (Web Text))

Max Activating Token Index: 819

Text #9

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0124. Min Act: -0.0003

Data Index: 1308473 (C4 (Web Text))

Max Activating Token Index: 517

Text #10

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0141. Min Act: -0.0003

Data Index: 188742 (C4 (Web Text))

Max Activating Token Index: 322

Text #11

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0113. Min Act: -0.0003

Data Index: 7857 (C4 (Web Text))

Max Activating Token Index: 647

Text #12

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0135. Min Act: -0.0003

Data Index: 50521 (C4 (Web Text))

Max Activating Token Index: 985

Text #13

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0107. Min Act: -0.0003

Data Index: 704707 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0137. Min Act: -0.0003

Data Index: 973964 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0129. Min Act: -0.0003

Data Index: 335628 (C4 (Web Text))

Max Activating Token Index: 868

Text #16

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0124. Min Act: -0.0003

Data Index: 794092 (C4 (Web Text))

Max Activating Token Index: 405

Text #17

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0127. Min Act: -0.0003

Data Index: 757078 (C4 (Web Text))

Max Activating Token Index: 476

Text #18

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0128. Min Act: -0.0003

Data Index: 497401 (C4 (Web Text))

Max Activating Token Index: 581

Text #19

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0116. Min Act: -0.0003

Data Index: 1079114 (C4 (Web Text))

Max Activating Token Index: 629