Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 34 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0177. Min Act: -0.0004

Data Index: 139787 (C4 (Web Text))

Max Activating Token Index: 579

Text #1

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0156. Min Act: -0.0004

Data Index: 1077464 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0153. Min Act: -0.0004

Data Index: 721695 (C4 (Web Text))

Max Activating Token Index: 454

Text #3

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0151. Min Act: -0.0004

Data Index: 225450 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0143. Min Act: -0.0004

Data Index: 1244182 (C4 (Web Text))

Max Activating Token Index: 169

Text #5

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0139. Min Act: -0.0004

Data Index: 761503 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0145. Min Act: -0.0004

Data Index: 1288995 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0149. Min Act: -0.0004

Data Index: 328930 (C4 (Web Text))

Max Activating Token Index: 900

Text #8

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0142. Min Act: -0.0004

Data Index: 508247 (C4 (Web Text))

Max Activating Token Index: 772

Text #9

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0117. Min Act: -0.0004

Data Index: 123809 (C4 (Web Text))

Max Activating Token Index: 699

Text #10

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0132. Min Act: -0.0004

Data Index: 1248968 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0124. Min Act: -0.0004

Data Index: 825390 (C4 (Web Text))

Max Activating Token Index: 948

Text #12

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0124. Min Act: -0.0004

Data Index: 1062779 (C4 (Web Text))

Max Activating Token Index: 926

Text #13

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0120. Min Act: -0.0004

Data Index: 1107400 (C4 (Web Text))

Max Activating Token Index: 581

Text #14

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0131. Min Act: -0.0004

Data Index: 700933 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0119. Min Act: -0.0004

Data Index: 413564 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0119. Min Act: -0.0004

Data Index: 594280 (C4 (Web Text))

Max Activating Token Index: 94

Text #17

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0128. Min Act: -0.0004

Data Index: 930379 (C4 (Web Text))

Max Activating Token Index: 306

Text #18

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0118. Min Act: -0.0004

Data Index: 259961 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0115. Min Act: -0.0004

Data Index: 264107 (C4 (Web Text))

Max Activating Token Index: 510