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

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

Neuron 1631 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0182. Min Act: -0.0006

Data Index: 407510 (C4 (Web Text))

Max Activating Token Index: 296

Text #1

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0147. Min Act: -0.0006

Data Index: 483687 (C4 (Web Text))

Max Activating Token Index: 668

Text #2

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0164. Min Act: -0.0006

Data Index: 1200970 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0157. Min Act: -0.0006

Data Index: 838281 (C4 (Web Text))

Max Activating Token Index: 158

Text #4

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0160. Min Act: -0.0006

Data Index: 756703 (C4 (Web Text))

Max Activating Token Index: 629

Text #5

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0158. Min Act: -0.0006

Data Index: 377040 (C4 (Web Text))

Max Activating Token Index: 56

Text #6

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0153. Min Act: -0.0006

Data Index: 1428092 (Python Code)

Max Activating Token Index: 6

Text #7

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0153. Min Act: -0.0006

Data Index: 1474872 (Python Code)

Max Activating Token Index: 617

Text #8

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0152. Min Act: -0.0006

Data Index: 1133707 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0154. Min Act: -0.0006

Data Index: 1176921 (C4 (Web Text))

Max Activating Token Index: 923

Text #10

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0140. Min Act: -0.0006

Data Index: 1396194 (Python Code)

Max Activating Token Index: 626

Text #11

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0146. Min Act: -0.0006

Data Index: 1275463 (C4 (Web Text))

Max Activating Token Index: 566

Text #12

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0159. Min Act: -0.0006

Data Index: 1330927 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0148. Min Act: -0.0006

Data Index: 92749 (C4 (Web Text))

Max Activating Token Index: 771

Text #14

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0144. Min Act: -0.0006

Data Index: 1569720 (Python Code)

Max Activating Token Index: 968

Text #15

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0151. Min Act: -0.0006

Data Index: 291789 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0148. Min Act: -0.0006

Data Index: 577991 (C4 (Web Text))

Max Activating Token Index: 883

Text #17

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0148. Min Act: -0.0006

Data Index: 1598520 (Python Code)

Max Activating Token Index: 727

Text #18

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0139. Min Act: -0.0006

Data Index: 537402 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0156. Min Act: -0.0005

Data Index: 1409396 (Python Code)

Max Activating Token Index: 790