Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2033 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1316. Min Act: -0.0000

Data Index: 1186718 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1283. Min Act: -0.0000

Data Index: 1325796 (C4 (Web Text))

Max Activating Token Index: 878

Text #2

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1156. Min Act: -0.0000

Data Index: 565399 (C4 (Web Text))

Max Activating Token Index: 386

Text #3

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1001. Min Act: -0.0000

Data Index: 914229 (C4 (Web Text))

Max Activating Token Index: 845

Text #4

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1004. Min Act: -0.0000

Data Index: 1347009 (C4 (Web Text))

Max Activating Token Index: 853

Text #5

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0938. Min Act: -0.0000

Data Index: 1655087 (Python Code)

Max Activating Token Index: 280

Text #6

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0999. Min Act: -0.0000

Data Index: 1549807 (Python Code)

Max Activating Token Index: 35

Text #7

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0938. Min Act: -0.0000

Data Index: 1231076 (C4 (Web Text))

Max Activating Token Index: 532

Text #8

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0831. Min Act: -0.0000

Data Index: 121710 (C4 (Web Text))

Max Activating Token Index: 791

Text #9

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0886. Min Act: -0.0000

Data Index: 1139010 (C4 (Web Text))

Max Activating Token Index: 520

Text #10

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0868. Min Act: -0.0000

Data Index: 36084 (C4 (Web Text))

Max Activating Token Index: 1011

Text #11

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0931. Min Act: -0.0000

Data Index: 515566 (C4 (Web Text))

Max Activating Token Index: 868

Text #12

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0915. Min Act: -0.0000

Data Index: 32035 (C4 (Web Text))

Max Activating Token Index: 470

Text #13

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0900. Min Act: -0.0000

Data Index: 339277 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0857. Min Act: -0.0000

Data Index: 752823 (C4 (Web Text))

Max Activating Token Index: 233

Text #15

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0799. Min Act: -0.0000

Data Index: 1441619 (Python Code)

Max Activating Token Index: 795

Text #16

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0874. Min Act: -0.0000

Data Index: 1333411 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0877. Min Act: -0.0000

Data Index: 1077571 (C4 (Web Text))

Max Activating Token Index: 221

Text #18

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0838. Min Act: -0.0000

Data Index: 450091 (C4 (Web Text))

Max Activating Token Index: 518

Text #19

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0837. Min Act: -0.0000

Data Index: 646517 (C4 (Web Text))

Max Activating Token Index: 256