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

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

Neuron 956 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: 0.1305. Min Range: -0.1305

Max Act: 0.1305. Min Act: -0.0003

Data Index: 755062 (C4 (Web Text))

Max Activating Token Index: 798

Text #1

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1149. Min Act: -0.0003

Data Index: 1232488 (C4 (Web Text))

Max Activating Token Index: 675

Text #2

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1227. Min Act: -0.0003

Data Index: 366850 (C4 (Web Text))

Max Activating Token Index: 692

Text #3

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1073. Min Act: -0.0003

Data Index: 418369 (C4 (Web Text))

Max Activating Token Index: 564

Text #4

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1173. Min Act: -0.0003

Data Index: 356103 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1065. Min Act: -0.0003

Data Index: 719418 (C4 (Web Text))

Max Activating Token Index: 1006

Text #6

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1073. Min Act: -0.0003

Data Index: 1007664 (C4 (Web Text))

Max Activating Token Index: 544

Text #7

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1116. Min Act: -0.0003

Data Index: 850865 (C4 (Web Text))

Max Activating Token Index: 306

Text #8

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0999. Min Act: -0.0003

Data Index: 1220720 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1000. Min Act: -0.0003

Data Index: 1022960 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0882. Min Act: -0.0003

Data Index: 182896 (C4 (Web Text))

Max Activating Token Index: 498

Text #11

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0927. Min Act: -0.0003

Data Index: 1021777 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0993. Min Act: -0.0003

Data Index: 570781 (C4 (Web Text))

Max Activating Token Index: 225

Text #13

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0975. Min Act: -0.0003

Data Index: 325556 (C4 (Web Text))

Max Activating Token Index: 564

Text #14

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0902. Min Act: -0.0003

Data Index: 1354753 (C4 (Web Text))

Max Activating Token Index: 998

Text #15

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0895. Min Act: -0.0003

Data Index: 375138 (C4 (Web Text))

Max Activating Token Index: 93

Text #16

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0910. Min Act: -0.0003

Data Index: 912187 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0873. Min Act: -0.0003

Data Index: 1173974 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0907. Min Act: -0.0003

Data Index: 595706 (C4 (Web Text))

Max Activating Token Index: 934

Text #19

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0866. Min Act: -0.0003

Data Index: 135595 (C4 (Web Text))

Max Activating Token Index: 310