Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3635 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0211. Min Act: -0.0002

Data Index: 716783 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0175. Min Act: -0.0002

Data Index: 1082436 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0154. Min Act: -0.0002

Data Index: 266780 (C4 (Web Text))

Max Activating Token Index: 389

Text #3

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0125. Min Act: -0.0002

Data Index: 1292858 (C4 (Web Text))

Max Activating Token Index: 873

Text #4

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0135. Min Act: -0.0002

Data Index: 248518 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0131. Min Act: -0.0002

Data Index: 987538 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0145. Min Act: -0.0002

Data Index: 1098673 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0104. Min Act: -0.0002

Data Index: 810622 (C4 (Web Text))

Max Activating Token Index: 815

Text #8

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0131. Min Act: -0.0002

Data Index: 249071 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0121. Min Act: -0.0002

Data Index: 1057944 (C4 (Web Text))

Max Activating Token Index: 346

Text #10

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0120. Min Act: -0.0002

Data Index: 21706 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0119. Min Act: -0.0002

Data Index: 160717 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0132. Min Act: -0.0002

Data Index: 828182 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0091. Min Act: -0.0002

Data Index: 1102969 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0121. Min Act: -0.0002

Data Index: 373731 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0109. Min Act: -0.0002

Data Index: 1112045 (C4 (Web Text))

Max Activating Token Index: 947

Text #16

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0095. Min Act: -0.0002

Data Index: 785858 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0109. Min Act: -0.0002

Data Index: 1083436 (C4 (Web Text))

Max Activating Token Index: 1004

Text #18

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0111. Min Act: -0.0002

Data Index: 780617 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0119. Min Act: -0.0002

Data Index: 426015 (C4 (Web Text))

Max Activating Token Index: 993