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

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

Neuron 368 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: 0.0178. Min Range: -0.0178

Max Act: 0.0178. Min Act: -0.0006

Data Index: 314647 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0166. Min Act: -0.0006

Data Index: 1175033 (C4 (Web Text))

Max Activating Token Index: 306

Text #2

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0154. Min Act: -0.0006

Data Index: 282732 (C4 (Web Text))

Max Activating Token Index: 850

Text #3

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0150. Min Act: -0.0006

Data Index: 1324323 (C4 (Web Text))

Max Activating Token Index: 398

Text #4

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0149. Min Act: -0.0006

Data Index: 664783 (C4 (Web Text))

Max Activating Token Index: 831

Text #5

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0146. Min Act: -0.0006

Data Index: 28671 (C4 (Web Text))

Max Activating Token Index: 430

Text #6

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0149. Min Act: -0.0006

Data Index: 1272023 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0144. Min Act: -0.0006

Data Index: 771571 (C4 (Web Text))

Max Activating Token Index: 274

Text #8

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0144. Min Act: -0.0005

Data Index: 1343654 (C4 (Web Text))

Max Activating Token Index: 877

Text #9

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0144. Min Act: -0.0006

Data Index: 1307438 (C4 (Web Text))

Max Activating Token Index: 408

Text #10

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0141. Min Act: -0.0005

Data Index: 484421 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0141. Min Act: -0.0006

Data Index: 335308 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0140. Min Act: -0.0006

Data Index: 1200274 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0136. Min Act: -0.0006

Data Index: 919888 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0141. Min Act: -0.0006

Data Index: 652171 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0137. Min Act: -0.0006

Data Index: 637133 (C4 (Web Text))

Max Activating Token Index: 755

Text #16

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0139. Min Act: -0.0005

Data Index: 250480 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0133. Min Act: -0.0006

Data Index: 770211 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0132. Min Act: -0.0006

Data Index: 565045 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0136. Min Act: -0.0006

Data Index: 1473189 (Python Code)

Max Activating Token Index: 968