Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1954 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.1064. Min Act: -0.0004

Data Index: 447082 (C4 (Web Text))

Max Activating Token Index: 648

Text #1

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.1081. Min Act: -0.0003

Data Index: 576328 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.1032. Min Act: -0.0003

Data Index: 1019568 (C4 (Web Text))

Max Activating Token Index: 723

Text #3

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0970. Min Act: -0.0004

Data Index: 88492 (C4 (Web Text))

Max Activating Token Index: 613

Text #4

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0965. Min Act: -0.0004

Data Index: 538374 (C4 (Web Text))

Max Activating Token Index: 443

Text #5

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0958. Min Act: -0.0003

Data Index: 346362 (C4 (Web Text))

Max Activating Token Index: 12

Text #6

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0968. Min Act: -0.0003

Data Index: 908587 (C4 (Web Text))

Max Activating Token Index: 352

Text #7

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0936. Min Act: -0.0003

Data Index: 862198 (C4 (Web Text))

Max Activating Token Index: 143

Text #8

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0918. Min Act: -0.0003

Data Index: 699077 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0949. Min Act: -0.0003

Data Index: 1279945 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0913. Min Act: -0.0003

Data Index: 1336385 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0909. Min Act: -0.0003

Data Index: 243176 (C4 (Web Text))

Max Activating Token Index: 891

Text #12

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0911. Min Act: -0.0003

Data Index: 339499 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0896. Min Act: -0.0003

Data Index: 745376 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0898. Min Act: -0.0004

Data Index: 1022960 (C4 (Web Text))

Max Activating Token Index: 724

Text #15

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0889. Min Act: -0.0003

Data Index: 509884 (C4 (Web Text))

Max Activating Token Index: 229

Text #16

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0891. Min Act: -0.0003

Data Index: 1246079 (C4 (Web Text))

Max Activating Token Index: 613

Text #17

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0889. Min Act: -0.0003

Data Index: 1138185 (C4 (Web Text))

Max Activating Token Index: 745

Text #18

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0856. Min Act: -0.0004

Data Index: 314475 (C4 (Web Text))

Max Activating Token Index: 322

Text #19

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0886. Min Act: -0.0004

Data Index: 442828 (C4 (Web Text))

Max Activating Token Index: 541