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

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

Neuron 493 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: 0.0157. Min Range: -0.0157

Max Act: 0.0157. Min Act: -0.0006

Data Index: 1385210 (Python Code)

Max Activating Token Index: 241

Text #1

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0149. Min Act: -0.0005

Data Index: 1364624 (Python Code)

Max Activating Token Index: 578

Text #2

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0150. Min Act: -0.0005

Data Index: 1463182 (Python Code)

Max Activating Token Index: 816

Text #3

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0143. Min Act: -0.0006

Data Index: 1480087 (Python Code)

Max Activating Token Index: 194

Text #4

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0141. Min Act: -0.0005

Data Index: 1582786 (Python Code)

Max Activating Token Index: 131

Text #5

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0135. Min Act: -0.0005

Data Index: 1377143 (Python Code)

Max Activating Token Index: 619

Text #6

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0133. Min Act: -0.0006

Data Index: 750110 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0129. Min Act: -0.0006

Data Index: 1634945 (Python Code)

Max Activating Token Index: 483

Text #8

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0129. Min Act: -0.0006

Data Index: 870967 (C4 (Web Text))

Max Activating Token Index: 601

Text #9

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0129. Min Act: -0.0005

Data Index: 1650257 (Python Code)

Max Activating Token Index: 116

Text #10

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0127. Min Act: -0.0006

Data Index: 1570455 (Python Code)

Max Activating Token Index: 48

Text #11

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0126. Min Act: -0.0006

Data Index: 1582542 (Python Code)

Max Activating Token Index: 784

Text #12

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0125. Min Act: -0.0005

Data Index: 1392901 (Python Code)

Max Activating Token Index: 366

Text #13

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0125. Min Act: -0.0006

Data Index: 526760 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0121. Min Act: -0.0005

Data Index: 527754 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0123. Min Act: -0.0006

Data Index: 1480616 (Python Code)

Max Activating Token Index: 396

Text #16

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0120. Min Act: -0.0006

Data Index: 1496761 (Python Code)

Max Activating Token Index: 319

Text #17

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0128. Min Act: -0.0006

Data Index: 550784 (C4 (Web Text))

Max Activating Token Index: 437

Text #18

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0123. Min Act: -0.0005

Data Index: 1381073 (Python Code)

Max Activating Token Index: 571

Text #19

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0122. Min Act: -0.0005

Data Index: 479431 (C4 (Web Text))

Max Activating Token Index: 577