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

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

Neuron 2581 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: 0.0159. Min Range: -0.0159

Max Act: 0.0159. Min Act: -0.0004

Data Index: 573692 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0144. Min Act: -0.0004

Data Index: 1066947 (C4 (Web Text))

Max Activating Token Index: 671

Text #2

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0145. Min Act: -0.0004

Data Index: 1172902 (C4 (Web Text))

Max Activating Token Index: 671

Text #3

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0132. Min Act: -0.0004

Data Index: 683031 (C4 (Web Text))

Max Activating Token Index: 487

Text #4

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0121. Min Act: -0.0004

Data Index: 551903 (C4 (Web Text))

Max Activating Token Index: 976

Text #5

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0126. Min Act: -0.0004

Data Index: 177924 (C4 (Web Text))

Max Activating Token Index: 843

Text #6

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0124. Min Act: -0.0004

Data Index: 611436 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0129. Min Act: -0.0004

Data Index: 719193 (C4 (Web Text))

Max Activating Token Index: 352

Text #8

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0106. Min Act: -0.0004

Data Index: 954382 (C4 (Web Text))

Max Activating Token Index: 749

Text #9

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0122. Min Act: -0.0004

Data Index: 289357 (C4 (Web Text))

Max Activating Token Index: 712

Text #10

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0115. Min Act: -0.0004

Data Index: 769264 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0124. Min Act: -0.0004

Data Index: 761176 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0107. Min Act: -0.0004

Data Index: 466505 (C4 (Web Text))

Max Activating Token Index: 852

Text #13

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0105. Min Act: -0.0004

Data Index: 192151 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0109. Min Act: -0.0004

Data Index: 402449 (C4 (Web Text))

Max Activating Token Index: 927

Text #15

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0101. Min Act: -0.0004

Data Index: 201901 (C4 (Web Text))

Max Activating Token Index: 135

Text #16

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0108. Min Act: -0.0004

Data Index: 102100 (C4 (Web Text))

Max Activating Token Index: 984

Text #17

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0100. Min Act: -0.0004

Data Index: 664921 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0115. Min Act: -0.0004

Data Index: 384581 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0104. Min Act: -0.0004

Data Index: 1012040 (C4 (Web Text))

Max Activating Token Index: 912