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

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

Neuron 305 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: 0.1607. Min Range: -0.1607

Max Act: 0.1607. Min Act: -0.0001

Data Index: 622107 (C4 (Web Text))

Max Activating Token Index: 295

Text #1

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1106. Min Act: -0.0001

Data Index: 195835 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1145. Min Act: -0.0001

Data Index: 1213828 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1146. Min Act: -0.0001

Data Index: 859849 (C4 (Web Text))

Max Activating Token Index: 897

Text #4

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.0939. Min Act: -0.0001

Data Index: 893038 (C4 (Web Text))

Max Activating Token Index: 409

Text #5

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.0971. Min Act: -0.0001

Data Index: 742250 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.0933. Min Act: -0.0001

Data Index: 104316 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.0930. Min Act: -0.0001

Data Index: 6764 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1000. Min Act: -0.0001

Data Index: 1150533 (C4 (Web Text))

Max Activating Token Index: 230

Text #9

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.0926. Min Act: -0.0001

Data Index: 824796 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.0929. Min Act: -0.0001

Data Index: 633085 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.0930. Min Act: -0.0001

Data Index: 990419 (C4 (Web Text))

Max Activating Token Index: 697

Text #12

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.0923. Min Act: -0.0001

Data Index: 775785 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.0905. Min Act: -0.0001

Data Index: 1116854 (C4 (Web Text))

Max Activating Token Index: 724

Text #14

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.0979. Min Act: -0.0001

Data Index: 965258 (C4 (Web Text))

Max Activating Token Index: 494

Text #15

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.0842. Min Act: -0.0001

Data Index: 60828 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.0938. Min Act: -0.0001

Data Index: 151148 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.0870. Min Act: -0.0001

Data Index: 914812 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.0899. Min Act: -0.0001

Data Index: 728052 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.0961. Min Act: -0.0001

Data Index: 100915 (C4 (Web Text))

Max Activating Token Index: 49