Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4064 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0209. Min Act: -0.0002

Data Index: 1507080 (Python Code)

Max Activating Token Index: 915

Text #1

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0187. Min Act: -0.0002

Data Index: 666575 (C4 (Web Text))

Max Activating Token Index: 435

Text #2

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0164. Min Act: -0.0002

Data Index: 1629610 (Python Code)

Max Activating Token Index: 962

Text #3

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0166. Min Act: -0.0003

Data Index: 1048633 (C4 (Web Text))

Max Activating Token Index: 509

Text #4

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0157. Min Act: -0.0002

Data Index: 648728 (C4 (Web Text))

Max Activating Token Index: 467

Text #5

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0155. Min Act: -0.0002

Data Index: 1480226 (Python Code)

Max Activating Token Index: 850

Text #6

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0153. Min Act: -0.0002

Data Index: 81845 (C4 (Web Text))

Max Activating Token Index: 976

Text #7

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0149. Min Act: -0.0002

Data Index: 1371679 (Python Code)

Max Activating Token Index: 979

Text #8

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0146. Min Act: -0.0002

Data Index: 1236195 (C4 (Web Text))

Max Activating Token Index: 412

Text #9

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0144. Min Act: -0.0002

Data Index: 1440643 (Python Code)

Max Activating Token Index: 553

Text #10

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0143. Min Act: -0.0002

Data Index: 1641296 (Python Code)

Max Activating Token Index: 618

Text #11

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0141. Min Act: -0.0002

Data Index: 1173730 (C4 (Web Text))

Max Activating Token Index: 522

Text #12

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0139. Min Act: -0.0002

Data Index: 592893 (C4 (Web Text))

Max Activating Token Index: 411

Text #13

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0142. Min Act: -0.0002

Data Index: 1554336 (Python Code)

Max Activating Token Index: 747

Text #14

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0140. Min Act: -0.0002

Data Index: 1483990 (Python Code)

Max Activating Token Index: 690

Text #15

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0140. Min Act: -0.0002

Data Index: 1158340 (C4 (Web Text))

Max Activating Token Index: 767

Text #16

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0137. Min Act: -0.0002

Data Index: 1379692 (Python Code)

Max Activating Token Index: 872

Text #17

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0136. Min Act: -0.0002

Data Index: 32786 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0138. Min Act: -0.0002

Data Index: 37778 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 0.0209. Min Range: -0.0209

Max Act: 0.0134. Min Act: -0.0002

Data Index: 1634791 (Python Code)

Max Activating Token Index: 674