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

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

Neuron 1902 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: 0.0150. Min Range: -0.0150

Max Act: 0.0149. Min Act: -0.0006

Data Index: 130810 (C4 (Web Text))

Max Activating Token Index: 551

Text #1

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0150. Min Act: -0.0006

Data Index: 666629 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0149. Min Act: -0.0006

Data Index: 1167138 (C4 (Web Text))

Max Activating Token Index: 1009

Text #3

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0143. Min Act: -0.0006

Data Index: 603490 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0144. Min Act: -0.0006

Data Index: 393366 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0143. Min Act: -0.0006

Data Index: 851328 (C4 (Web Text))

Max Activating Token Index: 141

Text #6

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0142. Min Act: -0.0006

Data Index: 88399 (C4 (Web Text))

Max Activating Token Index: 590

Text #7

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0140. Min Act: -0.0006

Data Index: 1129761 (C4 (Web Text))

Max Activating Token Index: 303

Text #8

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0135. Min Act: -0.0006

Data Index: 707226 (C4 (Web Text))

Max Activating Token Index: 394

Text #9

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0141. Min Act: -0.0006

Data Index: 921686 (C4 (Web Text))

Max Activating Token Index: 225

Text #10

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0132. Min Act: -0.0006

Data Index: 985151 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0132. Min Act: -0.0006

Data Index: 227459 (C4 (Web Text))

Max Activating Token Index: 499

Text #12

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0137. Min Act: -0.0006

Data Index: 133598 (C4 (Web Text))

Max Activating Token Index: 212

Text #13

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0131. Min Act: -0.0006

Data Index: 173298 (C4 (Web Text))

Max Activating Token Index: 708

Text #14

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0134. Min Act: -0.0006

Data Index: 692347 (C4 (Web Text))

Max Activating Token Index: 572

Text #15

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0136. Min Act: -0.0006

Data Index: 617933 (C4 (Web Text))

Max Activating Token Index: 934

Text #16

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0134. Min Act: -0.0006

Data Index: 957047 (C4 (Web Text))

Max Activating Token Index: 524

Text #17

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0133. Min Act: -0.0005

Data Index: 409452 (C4 (Web Text))

Max Activating Token Index: 809

Text #18

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0129. Min Act: -0.0006

Data Index: 566881 (C4 (Web Text))

Max Activating Token Index: 867

Text #19

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0132. Min Act: -0.0006

Data Index: 220908 (C4 (Web Text))

Max Activating Token Index: 652