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

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

Neuron 1466 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0178. Min Act: -0.0006

Data Index: 51960 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0176. Min Act: -0.0005

Data Index: 493629 (C4 (Web Text))

Max Activating Token Index: 618

Text #2

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0169. Min Act: -0.0006

Data Index: 559312 (C4 (Web Text))

Max Activating Token Index: 782

Text #3

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0166. Min Act: -0.0006

Data Index: 162527 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0164. Min Act: -0.0006

Data Index: 1021718 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0161. Min Act: -0.0006

Data Index: 1206769 (C4 (Web Text))

Max Activating Token Index: 271

Text #6

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0154. Min Act: -0.0006

Data Index: 762722 (C4 (Web Text))

Max Activating Token Index: 477

Text #7

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0155. Min Act: -0.0005

Data Index: 1430818 (Python Code)

Max Activating Token Index: 326

Text #8

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0151. Min Act: -0.0006

Data Index: 61505 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0154. Min Act: -0.0006

Data Index: 1198256 (C4 (Web Text))

Max Activating Token Index: 248

Text #10

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0152. Min Act: -0.0006

Data Index: 110384 (C4 (Web Text))

Max Activating Token Index: 607

Text #11

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0149. Min Act: -0.0006

Data Index: 638402 (C4 (Web Text))

Max Activating Token Index: 669

Text #12

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0153. Min Act: -0.0005

Data Index: 1425642 (Python Code)

Max Activating Token Index: 799

Text #13

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0148. Min Act: -0.0006

Data Index: 1216355 (C4 (Web Text))

Max Activating Token Index: 554

Text #14

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0151. Min Act: -0.0006

Data Index: 831346 (C4 (Web Text))

Max Activating Token Index: 109

Text #15

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0151. Min Act: -0.0005

Data Index: 685253 (C4 (Web Text))

Max Activating Token Index: 954

Text #16

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0149. Min Act: -0.0005

Data Index: 1642547 (Python Code)

Max Activating Token Index: 1010

Text #17

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0148. Min Act: -0.0006

Data Index: 130663 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0148. Min Act: -0.0006

Data Index: 1489231 (Python Code)

Max Activating Token Index: 226

Text #19

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0144. Min Act: -0.0006

Data Index: 30045 (C4 (Web Text))

Max Activating Token Index: 473