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

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

Neuron 2073 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: 0.0968. Min Range: -0.0968

Max Act: 0.0968. Min Act: -0.0002

Data Index: 1025693 (C4 (Web Text))

Max Activating Token Index: 570

Text #1

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0738. Min Act: -0.0002

Data Index: 100315 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0706. Min Act: -0.0002

Data Index: 250516 (C4 (Web Text))

Max Activating Token Index: 725

Text #3

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0696. Min Act: -0.0002

Data Index: 247575 (C4 (Web Text))

Max Activating Token Index: 629

Text #4

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0829. Min Act: -0.0002

Data Index: 21957 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0666. Min Act: -0.0002

Data Index: 165497 (C4 (Web Text))

Max Activating Token Index: 368

Text #6

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0561. Min Act: -0.0002

Data Index: 1320328 (C4 (Web Text))

Max Activating Token Index: 118

Text #7

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0638. Min Act: -0.0002

Data Index: 1103239 (C4 (Web Text))

Max Activating Token Index: 658

Text #8

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0655. Min Act: -0.0002

Data Index: 1093145 (C4 (Web Text))

Max Activating Token Index: 614

Text #9

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0707. Min Act: -0.0002

Data Index: 91431 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0607. Min Act: -0.0002

Data Index: 394616 (C4 (Web Text))

Max Activating Token Index: 755

Text #11

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0632. Min Act: -0.0002

Data Index: 846797 (C4 (Web Text))

Max Activating Token Index: 742

Text #12

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0598. Min Act: -0.0002

Data Index: 1359070 (C4 (Web Text))

Max Activating Token Index: 541

Text #13

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0555. Min Act: -0.0002

Data Index: 1146925 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0588. Min Act: -0.0002

Data Index: 982208 (C4 (Web Text))

Max Activating Token Index: 225

Text #15

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0584. Min Act: -0.0002

Data Index: 541248 (C4 (Web Text))

Max Activating Token Index: 718

Text #16

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0553. Min Act: -0.0002

Data Index: 1343483 (C4 (Web Text))

Max Activating Token Index: 117

Text #17

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0572. Min Act: -0.0002

Data Index: 846233 (C4 (Web Text))

Max Activating Token Index: 913

Text #18

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0574. Min Act: -0.0002

Data Index: 1187829 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0587. Min Act: -0.0002

Data Index: 1167758 (C4 (Web Text))

Max Activating Token Index: 755