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

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

Neuron 1293 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0146. Min Act: -0.0005

Data Index: 1395263 (Python Code)

Max Activating Token Index: 446

Text #1

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0142. Min Act: -0.0006

Data Index: 631721 (C4 (Web Text))

Max Activating Token Index: 541

Text #2

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0144. Min Act: -0.0006

Data Index: 335546 (C4 (Web Text))

Max Activating Token Index: 559

Text #3

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0143. Min Act: -0.0006

Data Index: 14326 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0142. Min Act: -0.0006

Data Index: 1258041 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0142. Min Act: -0.0006

Data Index: 575600 (C4 (Web Text))

Max Activating Token Index: 294

Text #6

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0141. Min Act: -0.0005

Data Index: 1503412 (Python Code)

Max Activating Token Index: 691

Text #7

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0137. Min Act: -0.0005

Data Index: 1401208 (Python Code)

Max Activating Token Index: 125

Text #8

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0140. Min Act: -0.0006

Data Index: 714742 (C4 (Web Text))

Max Activating Token Index: 448

Text #9

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0144. Min Act: -0.0006

Data Index: 46947 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0136. Min Act: -0.0006

Data Index: 679784 (C4 (Web Text))

Max Activating Token Index: 739

Text #11

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0137. Min Act: -0.0005

Data Index: 1636757 (Python Code)

Max Activating Token Index: 19

Text #12

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0139. Min Act: -0.0005

Data Index: 1492019 (Python Code)

Max Activating Token Index: 327

Text #13

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0136. Min Act: -0.0005

Data Index: 1565467 (Python Code)

Max Activating Token Index: 758

Text #14

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0142. Min Act: -0.0005

Data Index: 1370752 (Python Code)

Max Activating Token Index: 496

Text #15

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0137. Min Act: -0.0006

Data Index: 283038 (C4 (Web Text))

Max Activating Token Index: 742

Text #16

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0137. Min Act: -0.0006

Data Index: 604142 (C4 (Web Text))

Max Activating Token Index: 471

Text #17

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0136. Min Act: -0.0006

Data Index: 195097 (C4 (Web Text))

Max Activating Token Index: 561

Text #18

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0138. Min Act: -0.0005

Data Index: 1629224 (Python Code)

Max Activating Token Index: 341

Text #19

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0136. Min Act: -0.0006

Data Index: 508076 (C4 (Web Text))

Max Activating Token Index: 436