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

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

Neuron 3904 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0968. Min Act: -0.0001

Data Index: 911108 (C4 (Web Text))

Max Activating Token Index: 402

Text #1

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0743. Min Act: -0.0001

Data Index: 2945 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0738. Min Act: -0.0001

Data Index: 471722 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0746. Min Act: -0.0001

Data Index: 88195 (C4 (Web Text))

Max Activating Token Index: 657

Text #4

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0703. Min Act: -0.0001

Data Index: 997873 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0702. Min Act: -0.0001

Data Index: 1138933 (C4 (Web Text))

Max Activating Token Index: 632

Text #6

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0701. Min Act: -0.0001

Data Index: 1110857 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0736. Min Act: -0.0001

Data Index: 787303 (C4 (Web Text))

Max Activating Token Index: 657

Text #8

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0681. Min Act: -0.0001

Data Index: 862778 (C4 (Web Text))

Max Activating Token Index: 595

Text #9

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0625. Min Act: -0.0001

Data Index: 1124224 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0669. Min Act: -0.0001

Data Index: 116771 (C4 (Web Text))

Max Activating Token Index: 997

Text #11

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0736. Min Act: -0.0001

Data Index: 737425 (C4 (Web Text))

Max Activating Token Index: 849

Text #12

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0653. Min Act: -0.0001

Data Index: 1183263 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0639. Min Act: -0.0001

Data Index: 1182979 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0624. Min Act: -0.0001

Data Index: 1329888 (C4 (Web Text))

Max Activating Token Index: 647

Text #15

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0607. Min Act: -0.0001

Data Index: 125943 (C4 (Web Text))

Max Activating Token Index: 481

Text #16

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0600. Min Act: -0.0001

Data Index: 671449 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0515. Min Act: -0.0001

Data Index: 879121 (C4 (Web Text))

Max Activating Token Index: 992

Text #18

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0558. Min Act: -0.0001

Data Index: 1216077 (C4 (Web Text))

Max Activating Token Index: 370

Text #19

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0563. Min Act: -0.0001

Data Index: 304011 (C4 (Web Text))

Max Activating Token Index: 314