Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3215 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0980. Min Act: -0.0002

Data Index: 1296250 (C4 (Web Text))

Max Activating Token Index: 963

Text #1

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0965. Min Act: -0.0002

Data Index: 895950 (C4 (Web Text))

Max Activating Token Index: 399

Text #2

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0935. Min Act: -0.0002

Data Index: 96927 (C4 (Web Text))

Max Activating Token Index: 397

Text #3

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0951. Min Act: -0.0002

Data Index: 1652679 (Python Code)

Max Activating Token Index: 104

Text #4

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0939. Min Act: -0.0002

Data Index: 486098 (C4 (Web Text))

Max Activating Token Index: 399

Text #5

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0874. Min Act: -0.0002

Data Index: 1103814 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0849. Min Act: -0.0002

Data Index: 810035 (C4 (Web Text))

Max Activating Token Index: 952

Text #7

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0882. Min Act: -0.0002

Data Index: 1175643 (C4 (Web Text))

Max Activating Token Index: 40

Text #8

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0851. Min Act: -0.0002

Data Index: 1204927 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0837. Min Act: -0.0002

Data Index: 981607 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0806. Min Act: -0.0002

Data Index: 1114005 (C4 (Web Text))

Max Activating Token Index: 923

Text #11

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0849. Min Act: -0.0002

Data Index: 740983 (C4 (Web Text))

Max Activating Token Index: 515

Text #12

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0812. Min Act: -0.0002

Data Index: 805048 (C4 (Web Text))

Max Activating Token Index: 930

Text #13

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0780. Min Act: -0.0002

Data Index: 1131406 (C4 (Web Text))

Max Activating Token Index: 173

Text #14

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0790. Min Act: -0.0002

Data Index: 1503405 (Python Code)

Max Activating Token Index: 67

Text #15

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0796. Min Act: -0.0002

Data Index: 1335347 (C4 (Web Text))

Max Activating Token Index: 244

Text #16

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0796. Min Act: -0.0002

Data Index: 1310863 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0762. Min Act: -0.0002

Data Index: 1281838 (C4 (Web Text))

Max Activating Token Index: 732

Text #18

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0788. Min Act: -0.0002

Data Index: 365628 (C4 (Web Text))

Max Activating Token Index: 633

Text #19

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0762. Min Act: -0.0002

Data Index: 933046 (C4 (Web Text))

Max Activating Token Index: 432