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

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

Neuron 701 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.1125. Min Act: -0.0002

Data Index: 748437 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.1062. Min Act: -0.0002

Data Index: 451703 (C4 (Web Text))

Max Activating Token Index: 846

Text #2

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.1085. Min Act: -0.0002

Data Index: 743776 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.1036. Min Act: -0.0002

Data Index: 599283 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.1008. Min Act: -0.0002

Data Index: 48361 (C4 (Web Text))

Max Activating Token Index: 465

Text #5

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0973. Min Act: -0.0002

Data Index: 1255447 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0929. Min Act: -0.0002

Data Index: 1272096 (C4 (Web Text))

Max Activating Token Index: 976

Text #7

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0946. Min Act: -0.0002

Data Index: 1084789 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0880. Min Act: -0.0002

Data Index: 1087563 (C4 (Web Text))

Max Activating Token Index: 498

Text #9

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0947. Min Act: -0.0002

Data Index: 112088 (C4 (Web Text))

Max Activating Token Index: 515

Text #10

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0915. Min Act: -0.0002

Data Index: 1030456 (C4 (Web Text))

Max Activating Token Index: 446

Text #11

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0915. Min Act: -0.0002

Data Index: 169170 (C4 (Web Text))

Max Activating Token Index: 163

Text #12

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0881. Min Act: -0.0002

Data Index: 1212102 (C4 (Web Text))

Max Activating Token Index: 791

Text #13

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0871. Min Act: -0.0002

Data Index: 1023066 (C4 (Web Text))

Max Activating Token Index: 438

Text #14

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0824. Min Act: -0.0002

Data Index: 114223 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0818. Min Act: -0.0002

Data Index: 511520 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0786. Min Act: -0.0002

Data Index: 821438 (C4 (Web Text))

Max Activating Token Index: 420

Text #17

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0803. Min Act: -0.0002

Data Index: 1251243 (C4 (Web Text))

Max Activating Token Index: 697

Text #18

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0811. Min Act: -0.0002

Data Index: 1244991 (C4 (Web Text))

Max Activating Token Index: 528

Text #19

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0830. Min Act: -0.0002

Data Index: 243832 (C4 (Web Text))

Max Activating Token Index: 142