Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1638 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0170. Min Act: -0.0005

Data Index: 1274794 (C4 (Web Text))

Max Activating Token Index: 782

Text #1

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0162. Min Act: -0.0004

Data Index: 1273505 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0160. Min Act: -0.0005

Data Index: 241017 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0156. Min Act: -0.0005

Data Index: 204326 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0154. Min Act: -0.0005

Data Index: 853064 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0154. Min Act: -0.0005

Data Index: 856417 (C4 (Web Text))

Max Activating Token Index: 727

Text #6

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0154. Min Act: -0.0004

Data Index: 972431 (C4 (Web Text))

Max Activating Token Index: 276

Text #7

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0153. Min Act: -0.0004

Data Index: 1014169 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0152. Min Act: -0.0004

Data Index: 1047795 (C4 (Web Text))

Max Activating Token Index: 509

Text #9

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0152. Min Act: -0.0005

Data Index: 84420 (C4 (Web Text))

Max Activating Token Index: 625

Text #10

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0148. Min Act: -0.0004

Data Index: 418312 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0151. Min Act: -0.0004

Data Index: 1291199 (C4 (Web Text))

Max Activating Token Index: 522

Text #12

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0150. Min Act: -0.0004

Data Index: 970712 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0147. Min Act: -0.0004

Data Index: 62304 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0146. Min Act: -0.0005

Data Index: 887020 (C4 (Web Text))

Max Activating Token Index: 754

Text #15

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0146. Min Act: -0.0005

Data Index: 713290 (C4 (Web Text))

Max Activating Token Index: 584

Text #16

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0149. Min Act: -0.0005

Data Index: 1050424 (C4 (Web Text))

Max Activating Token Index: 516

Text #17

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0148. Min Act: -0.0005

Data Index: 282872 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0148. Min Act: -0.0004

Data Index: 1241002 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0148. Min Act: -0.0005

Data Index: 687276 (C4 (Web Text))

Max Activating Token Index: 568