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

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

Neuron 237 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.1081. Min Act: -0.0003

Data Index: 800369 (C4 (Web Text))

Max Activating Token Index: 290

Text #1

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.1039. Min Act: -0.0003

Data Index: 218719 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.1009. Min Act: -0.0003

Data Index: 213103 (C4 (Web Text))

Max Activating Token Index: 41

Text #3

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0930. Min Act: -0.0003

Data Index: 951380 (C4 (Web Text))

Max Activating Token Index: 129

Text #4

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0965. Min Act: -0.0003

Data Index: 390510 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0923. Min Act: -0.0003

Data Index: 515127 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0875. Min Act: -0.0003

Data Index: 1053950 (C4 (Web Text))

Max Activating Token Index: 965

Text #7

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0938. Min Act: -0.0003

Data Index: 96894 (C4 (Web Text))

Max Activating Token Index: 403

Text #8

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0934. Min Act: -0.0003

Data Index: 1248990 (C4 (Web Text))

Max Activating Token Index: 63

Text #9

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0929. Min Act: -0.0003

Data Index: 535054 (C4 (Web Text))

Max Activating Token Index: 246

Text #10

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0892. Min Act: -0.0003

Data Index: 541827 (C4 (Web Text))

Max Activating Token Index: 135

Text #11

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0854. Min Act: -0.0003

Data Index: 1048178 (C4 (Web Text))

Max Activating Token Index: 83

Text #12

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0882. Min Act: -0.0003

Data Index: 81148 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0873. Min Act: -0.0003

Data Index: 347609 (C4 (Web Text))

Max Activating Token Index: 1003

Text #14

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0902. Min Act: -0.0003

Data Index: 292651 (C4 (Web Text))

Max Activating Token Index: 454

Text #15

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0866. Min Act: -0.0003

Data Index: 1142727 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0871. Min Act: -0.0003

Data Index: 721816 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0892. Min Act: -0.0003

Data Index: 843505 (C4 (Web Text))

Max Activating Token Index: 245

Text #18

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0891. Min Act: -0.0003

Data Index: 840518 (C4 (Web Text))

Max Activating Token Index: 104

Text #19

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0825. Min Act: -0.0003

Data Index: 743173 (C4 (Web Text))

Max Activating Token Index: 832