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

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

Neuron 754 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1309. Min Act: -0.0001

Data Index: 396240 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1021. Min Act: -0.0001

Data Index: 650581 (C4 (Web Text))

Max Activating Token Index: 274

Text #2

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0993. Min Act: -0.0001

Data Index: 335766 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1042. Min Act: -0.0001

Data Index: 28587 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0994. Min Act: -0.0001

Data Index: 580820 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0993. Min Act: -0.0001

Data Index: 773875 (C4 (Web Text))

Max Activating Token Index: 136

Text #6

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0888. Min Act: -0.0001

Data Index: 1135034 (C4 (Web Text))

Max Activating Token Index: 525

Text #7

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1008. Min Act: -0.0001

Data Index: 1184614 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0890. Min Act: -0.0001

Data Index: 395525 (C4 (Web Text))

Max Activating Token Index: 722

Text #9

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0909. Min Act: -0.0001

Data Index: 869330 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0935. Min Act: -0.0001

Data Index: 923598 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0894. Min Act: -0.0001

Data Index: 417707 (C4 (Web Text))

Max Activating Token Index: 375

Text #12

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0858. Min Act: -0.0001

Data Index: 159171 (C4 (Web Text))

Max Activating Token Index: 741

Text #13

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0891. Min Act: -0.0001

Data Index: 289614 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0886. Min Act: -0.0001

Data Index: 1087544 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0869. Min Act: -0.0001

Data Index: 1322570 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0869. Min Act: -0.0001

Data Index: 187395 (C4 (Web Text))

Max Activating Token Index: 833

Text #17

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0859. Min Act: -0.0001

Data Index: 43586 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0893. Min Act: -0.0001

Data Index: 1268331 (C4 (Web Text))

Max Activating Token Index: 204

Text #19

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0776. Min Act: -0.0001

Data Index: 75564 (C4 (Web Text))

Max Activating Token Index: 924