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

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

Neuron 77 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.1118. Min Act: -0.0001

Data Index: 429685 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.1109. Min Act: -0.0001

Data Index: 363010 (C4 (Web Text))

Max Activating Token Index: 216

Text #2

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.1045. Min Act: -0.0001

Data Index: 498578 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.1064. Min Act: -0.0001

Data Index: 1017683 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0991. Min Act: -0.0001

Data Index: 1032535 (C4 (Web Text))

Max Activating Token Index: 584

Text #5

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0965. Min Act: -0.0001

Data Index: 84199 (C4 (Web Text))

Max Activating Token Index: 692

Text #6

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.1008. Min Act: -0.0001

Data Index: 940766 (C4 (Web Text))

Max Activating Token Index: 799

Text #7

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0924. Min Act: -0.0001

Data Index: 594414 (C4 (Web Text))

Max Activating Token Index: 850

Text #8

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0980. Min Act: -0.0001

Data Index: 96968 (C4 (Web Text))

Max Activating Token Index: 196

Text #9

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0979. Min Act: -0.0001

Data Index: 523424 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0970. Min Act: -0.0001

Data Index: 496577 (C4 (Web Text))

Max Activating Token Index: 775

Text #11

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0895. Min Act: -0.0001

Data Index: 517494 (C4 (Web Text))

Max Activating Token Index: 352

Text #12

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0983. Min Act: -0.0001

Data Index: 288779 (C4 (Web Text))

Max Activating Token Index: 258

Text #13

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0921. Min Act: -0.0001

Data Index: 1023683 (C4 (Web Text))

Max Activating Token Index: 446

Text #14

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0948. Min Act: -0.0001

Data Index: 32830 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0940. Min Act: -0.0001

Data Index: 387839 (C4 (Web Text))

Max Activating Token Index: 780

Text #16

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0980. Min Act: -0.0001

Data Index: 970274 (C4 (Web Text))

Max Activating Token Index: 504

Text #17

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0939. Min Act: -0.0001

Data Index: 1355681 (C4 (Web Text))

Max Activating Token Index: 216

Text #18

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0934. Min Act: -0.0001

Data Index: 958955 (C4 (Web Text))

Max Activating Token Index: 840

Text #19

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.1002. Min Act: -0.0001

Data Index: 1324011 (C4 (Web Text))

Max Activating Token Index: 658