Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 512 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0181. Min Act: -0.0002

Data Index: 842047 (C4 (Web Text))

Max Activating Token Index: 731

Text #1

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0158. Min Act: -0.0002

Data Index: 858691 (C4 (Web Text))

Max Activating Token Index: 934

Text #2

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0153. Min Act: -0.0002

Data Index: 837462 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0154. Min Act: -0.0002

Data Index: 270395 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0152. Min Act: -0.0002

Data Index: 648712 (C4 (Web Text))

Max Activating Token Index: 294

Text #5

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0151. Min Act: -0.0002

Data Index: 532303 (C4 (Web Text))

Max Activating Token Index: 573

Text #6

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0149. Min Act: -0.0002

Data Index: 329350 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0144. Min Act: -0.0002

Data Index: 230675 (C4 (Web Text))

Max Activating Token Index: 551

Text #8

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0140. Min Act: -0.0002

Data Index: 825786 (C4 (Web Text))

Max Activating Token Index: 694

Text #9

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0142. Min Act: -0.0002

Data Index: 1136037 (C4 (Web Text))

Max Activating Token Index: 918

Text #10

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0142. Min Act: -0.0002

Data Index: 375592 (C4 (Web Text))

Max Activating Token Index: 535

Text #11

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0141. Min Act: -0.0002

Data Index: 1201758 (C4 (Web Text))

Max Activating Token Index: 500

Text #12

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0140. Min Act: -0.0002

Data Index: 1247364 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0138. Min Act: -0.0002

Data Index: 493300 (C4 (Web Text))

Max Activating Token Index: 261

Text #14

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0138. Min Act: -0.0002

Data Index: 372381 (C4 (Web Text))

Max Activating Token Index: 395

Text #15

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0138. Min Act: -0.0002

Data Index: 540848 (C4 (Web Text))

Max Activating Token Index: 820

Text #16

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0137. Min Act: -0.0002

Data Index: 1013620 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0136. Min Act: -0.0002

Data Index: 420658 (C4 (Web Text))

Max Activating Token Index: 831

Text #18

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0136. Min Act: -0.0002

Data Index: 247098 (C4 (Web Text))

Max Activating Token Index: 877

Text #19

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0134. Min Act: -0.0002

Data Index: 448133 (C4 (Web Text))

Max Activating Token Index: 828