Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1805 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0165. Min Act: -0.0006

Data Index: 251086 (C4 (Web Text))

Max Activating Token Index: 766

Text #1

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0161. Min Act: -0.0006

Data Index: 223113 (C4 (Web Text))

Max Activating Token Index: 206

Text #2

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0162. Min Act: -0.0006

Data Index: 464003 (C4 (Web Text))

Max Activating Token Index: 956

Text #3

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0155. Min Act: -0.0006

Data Index: 1225387 (C4 (Web Text))

Max Activating Token Index: 642

Text #4

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0158. Min Act: -0.0006

Data Index: 723900 (C4 (Web Text))

Max Activating Token Index: 518

Text #5

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0156. Min Act: -0.0006

Data Index: 318324 (C4 (Web Text))

Max Activating Token Index: 453

Text #6

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0149. Min Act: -0.0006

Data Index: 169479 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0152. Min Act: -0.0006

Data Index: 1328530 (C4 (Web Text))

Max Activating Token Index: 312

Text #8

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0154. Min Act: -0.0006

Data Index: 1213921 (C4 (Web Text))

Max Activating Token Index: 510

Text #9

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0159. Min Act: -0.0006

Data Index: 1545744 (Python Code)

Max Activating Token Index: 415

Text #10

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0155. Min Act: -0.0006

Data Index: 1362131 (Python Code)

Max Activating Token Index: 198

Text #11

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0156. Min Act: -0.0006

Data Index: 345526 (C4 (Web Text))

Max Activating Token Index: 735

Text #12

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0149. Min Act: -0.0006

Data Index: 603639 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0152. Min Act: -0.0006

Data Index: 283669 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0150. Min Act: -0.0006

Data Index: 648602 (C4 (Web Text))

Max Activating Token Index: 462

Text #15

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0149. Min Act: -0.0006

Data Index: 639242 (C4 (Web Text))

Max Activating Token Index: 581

Text #16

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0150. Min Act: -0.0006

Data Index: 1521633 (Python Code)

Max Activating Token Index: 555

Text #17

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0155. Min Act: -0.0006

Data Index: 1486194 (Python Code)

Max Activating Token Index: 918

Text #18

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0151. Min Act: -0.0006

Data Index: 760972 (C4 (Web Text))

Max Activating Token Index: 702

Text #19

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0146. Min Act: -0.0006

Data Index: 656636 (C4 (Web Text))

Max Activating Token Index: 212