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

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

Neuron 1522 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4048. Min Range: -0.4048

Max Act: 0.4048. Min Act: -0.0001

Data Index: 1343173 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 0.4048. Min Range: -0.4048

Max Act: 0.3776. Min Act: -0.0001

Data Index: 1057777 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 0.4048. Min Range: -0.4048

Max Act: 0.3524. Min Act: -0.0001

Data Index: 1319903 (C4 (Web Text))

Max Activating Token Index: 475

Text #3

Max Range: 0.4048. Min Range: -0.4048

Max Act: 0.3390. Min Act: -0.0001

Data Index: 882995 (C4 (Web Text))

Max Activating Token Index: 812

Text #4

Max Range: 0.4048. Min Range: -0.4048

Max Act: 0.3370. Min Act: -0.0001

Data Index: 1280996 (C4 (Web Text))

Max Activating Token Index: 303

Text #5

Max Range: 0.4048. Min Range: -0.4048

Max Act: 0.3182. Min Act: -0.0001

Data Index: 860771 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 0.4048. Min Range: -0.4048

Max Act: 0.3170. Min Act: -0.0001

Data Index: 710106 (C4 (Web Text))

Max Activating Token Index: 933

Text #7

Max Range: 0.4048. Min Range: -0.4048

Max Act: 0.3022. Min Act: -0.0001

Data Index: 764991 (C4 (Web Text))

Max Activating Token Index: 429

Text #8

Max Range: 0.4048. Min Range: -0.4048

Max Act: 0.3040. Min Act: -0.0001

Data Index: 873432 (C4 (Web Text))

Max Activating Token Index: 484

Text #9

Max Range: 0.4048. Min Range: -0.4048

Max Act: 0.3040. Min Act: -0.0001

Data Index: 1133411 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 0.4048. Min Range: -0.4048

Max Act: 0.2951. Min Act: -0.0001

Data Index: 803571 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 0.4048. Min Range: -0.4048

Max Act: 0.2927. Min Act: -0.0001

Data Index: 1060103 (C4 (Web Text))

Max Activating Token Index: 270

Text #12

Max Range: 0.4048. Min Range: -0.4048

Max Act: 0.2773. Min Act: -0.0001

Data Index: 778061 (C4 (Web Text))

Max Activating Token Index: 755

Text #13

Max Range: 0.4048. Min Range: -0.4048

Max Act: 0.2920. Min Act: -0.0001

Data Index: 350823 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 0.4048. Min Range: -0.4048

Max Act: 0.2906. Min Act: -0.0001

Data Index: 845295 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 0.4048. Min Range: -0.4048

Max Act: 0.2817. Min Act: -0.0001

Data Index: 955015 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 0.4048. Min Range: -0.4048

Max Act: 0.2830. Min Act: -0.0001

Data Index: 1105253 (C4 (Web Text))

Max Activating Token Index: 118

Text #17

Max Range: 0.4048. Min Range: -0.4048

Max Act: 0.2792. Min Act: -0.0001

Data Index: 567275 (C4 (Web Text))

Max Activating Token Index: 780

Text #18

Max Range: 0.4048. Min Range: -0.4048

Max Act: 0.2619. Min Act: -0.0001

Data Index: 284447 (C4 (Web Text))

Max Activating Token Index: 420

Text #19

Max Range: 0.4048. Min Range: -0.4048

Max Act: 0.2772. Min Act: -0.0001

Data Index: 388179 (C4 (Web Text))

Max Activating Token Index: 31