Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1064 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0160. Min Act: -0.0004

Data Index: 737724 (C4 (Web Text))

Max Activating Token Index: 387

Text #1

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0145. Min Act: -0.0004

Data Index: 974921 (C4 (Web Text))

Max Activating Token Index: 839

Text #2

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0141. Min Act: -0.0004

Data Index: 1068227 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0129. Min Act: -0.0004

Data Index: 592435 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0132. Min Act: -0.0004

Data Index: 856331 (C4 (Web Text))

Max Activating Token Index: 730

Text #5

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0123. Min Act: -0.0004

Data Index: 15735 (C4 (Web Text))

Max Activating Token Index: 519

Text #6

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0133. Min Act: -0.0004

Data Index: 853150 (C4 (Web Text))

Max Activating Token Index: 810

Text #7

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0129. Min Act: -0.0004

Data Index: 931542 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0125. Min Act: -0.0004

Data Index: 444196 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0125. Min Act: -0.0004

Data Index: 505491 (C4 (Web Text))

Max Activating Token Index: 75

Text #10

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0126. Min Act: -0.0004

Data Index: 509761 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0122. Min Act: -0.0004

Data Index: 873515 (C4 (Web Text))

Max Activating Token Index: 698

Text #12

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0120. Min Act: -0.0004

Data Index: 956180 (C4 (Web Text))

Max Activating Token Index: 366

Text #13

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0123. Min Act: -0.0004

Data Index: 310390 (C4 (Web Text))

Max Activating Token Index: 641

Text #14

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0125. Min Act: -0.0004

Data Index: 1254169 (C4 (Web Text))

Max Activating Token Index: 1016

Text #15

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0115. Min Act: -0.0004

Data Index: 920975 (C4 (Web Text))

Max Activating Token Index: 225

Text #16

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0111. Min Act: -0.0004

Data Index: 24235 (C4 (Web Text))

Max Activating Token Index: 644

Text #17

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0117. Min Act: -0.0004

Data Index: 773094 (C4 (Web Text))

Max Activating Token Index: 100

Text #18

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0113. Min Act: -0.0004

Data Index: 312271 (C4 (Web Text))

Max Activating Token Index: 197

Text #19

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0118. Min Act: -0.0004

Data Index: 202861 (C4 (Web Text))

Max Activating Token Index: 8