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

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

Neuron 1480 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: 0.0153. Min Range: -0.0153

Max Act: 0.0152. Min Act: -0.0006

Data Index: 859097 (C4 (Web Text))

Max Activating Token Index: 534

Text #1

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0153. Min Act: -0.0006

Data Index: 780932 (C4 (Web Text))

Max Activating Token Index: 903

Text #2

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0144. Min Act: -0.0006

Data Index: 361725 (C4 (Web Text))

Max Activating Token Index: 622

Text #3

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0145. Min Act: -0.0006

Data Index: 213146 (C4 (Web Text))

Max Activating Token Index: 547

Text #4

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0141. Min Act: -0.0006

Data Index: 451887 (C4 (Web Text))

Max Activating Token Index: 244

Text #5

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0139. Min Act: -0.0006

Data Index: 997925 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0138. Min Act: -0.0006

Data Index: 203510 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0135. Min Act: -0.0006

Data Index: 242238 (C4 (Web Text))

Max Activating Token Index: 596

Text #8

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0137. Min Act: -0.0007

Data Index: 998646 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0133. Min Act: -0.0006

Data Index: 557419 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0132. Min Act: -0.0006

Data Index: 910720 (C4 (Web Text))

Max Activating Token Index: 286

Text #11

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0136. Min Act: -0.0006

Data Index: 309314 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0132. Min Act: -0.0006

Data Index: 658938 (C4 (Web Text))

Max Activating Token Index: 618

Text #13

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0130. Min Act: -0.0006

Data Index: 970144 (C4 (Web Text))

Max Activating Token Index: 489

Text #14

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0131. Min Act: -0.0006

Data Index: 449756 (C4 (Web Text))

Max Activating Token Index: 232

Text #15

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0132. Min Act: -0.0006

Data Index: 583599 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0129. Min Act: -0.0006

Data Index: 999407 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0131. Min Act: -0.0006

Data Index: 1262899 (C4 (Web Text))

Max Activating Token Index: 150

Text #18

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0131. Min Act: -0.0006

Data Index: 236878 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0129. Min Act: -0.0006

Data Index: 1351766 (C4 (Web Text))

Max Activating Token Index: 200