Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1922 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.1021. Min Act: -0.0001

Data Index: 390664 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.1067. Min Act: -0.0001

Data Index: 740064 (C4 (Web Text))

Max Activating Token Index: 322

Text #2

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.1057. Min Act: -0.0001

Data Index: 373003 (C4 (Web Text))

Max Activating Token Index: 272

Text #3

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0989. Min Act: -0.0001

Data Index: 1206109 (C4 (Web Text))

Max Activating Token Index: 765

Text #4

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.1073. Min Act: -0.0001

Data Index: 622563 (C4 (Web Text))

Max Activating Token Index: 480

Text #5

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0945. Min Act: -0.0001

Data Index: 1041497 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.1032. Min Act: -0.0001

Data Index: 903904 (C4 (Web Text))

Max Activating Token Index: 627

Text #7

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0934. Min Act: -0.0001

Data Index: 191550 (C4 (Web Text))

Max Activating Token Index: 558

Text #8

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.1002. Min Act: -0.0001

Data Index: 419539 (C4 (Web Text))

Max Activating Token Index: 310

Text #9

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.1021. Min Act: -0.0001

Data Index: 687132 (C4 (Web Text))

Max Activating Token Index: 929

Text #10

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.1135. Min Act: -0.0001

Data Index: 876199 (C4 (Web Text))

Max Activating Token Index: 537

Text #11

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0955. Min Act: -0.0001

Data Index: 170866 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0958. Min Act: -0.0001

Data Index: 1156291 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.1012. Min Act: -0.0001

Data Index: 809271 (C4 (Web Text))

Max Activating Token Index: 117

Text #14

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.1019. Min Act: -0.0001

Data Index: 844159 (C4 (Web Text))

Max Activating Token Index: 430

Text #15

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0972. Min Act: -0.0001

Data Index: 960114 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0989. Min Act: -0.0001

Data Index: 79214 (C4 (Web Text))

Max Activating Token Index: 212

Text #17

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.1051. Min Act: -0.0001

Data Index: 601004 (C4 (Web Text))

Max Activating Token Index: 102

Text #18

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.1124. Min Act: -0.0001

Data Index: 102174 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0929. Min Act: -0.0001

Data Index: 455653 (C4 (Web Text))

Max Activating Token Index: 412