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

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

Neuron 611 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: 0.0168. Min Range: -0.0168

Max Act: 0.0168. Min Act: -0.0006

Data Index: 568618 (C4 (Web Text))

Max Activating Token Index: 777

Text #1

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0164. Min Act: -0.0006

Data Index: 1083719 (C4 (Web Text))

Max Activating Token Index: 272

Text #2

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0155. Min Act: -0.0006

Data Index: 1230249 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0152. Min Act: -0.0006

Data Index: 859038 (C4 (Web Text))

Max Activating Token Index: 278

Text #4

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0145. Min Act: -0.0006

Data Index: 236378 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0144. Min Act: -0.0006

Data Index: 266757 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0147. Min Act: -0.0006

Data Index: 1303014 (C4 (Web Text))

Max Activating Token Index: 625

Text #7

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0146. Min Act: -0.0006

Data Index: 422641 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0149. Min Act: -0.0006

Data Index: 799490 (C4 (Web Text))

Max Activating Token Index: 520

Text #9

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0146. Min Act: -0.0006

Data Index: 519170 (C4 (Web Text))

Max Activating Token Index: 317

Text #10

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0134. Min Act: -0.0006

Data Index: 740690 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0138. Min Act: -0.0006

Data Index: 850908 (C4 (Web Text))

Max Activating Token Index: 735

Text #12

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0137. Min Act: -0.0006

Data Index: 457787 (C4 (Web Text))

Max Activating Token Index: 803

Text #13

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0136. Min Act: -0.0006

Data Index: 421290 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0139. Min Act: -0.0006

Data Index: 576608 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0142. Min Act: -0.0006

Data Index: 1204658 (C4 (Web Text))

Max Activating Token Index: 611

Text #16

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0138. Min Act: -0.0006

Data Index: 926011 (C4 (Web Text))

Max Activating Token Index: 783

Text #17

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0137. Min Act: -0.0006

Data Index: 1038892 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0137. Min Act: -0.0006

Data Index: 385909 (C4 (Web Text))

Max Activating Token Index: 122

Text #19

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0144. Min Act: -0.0006

Data Index: 672488 (C4 (Web Text))

Max Activating Token Index: 844