Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3144 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0841. Min Act: -0.0001

Data Index: 1432438 (Python Code)

Max Activating Token Index: 751

Text #1

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0800. Min Act: -0.0000

Data Index: 632882 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0729. Min Act: -0.0001

Data Index: 919601 (C4 (Web Text))

Max Activating Token Index: 523

Text #3

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0771. Min Act: -0.0000

Data Index: 984427 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0722. Min Act: -0.0000

Data Index: 3585 (C4 (Web Text))

Max Activating Token Index: 476

Text #5

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0682. Min Act: -0.0001

Data Index: 1061854 (C4 (Web Text))

Max Activating Token Index: 498

Text #6

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0704. Min Act: -0.0001

Data Index: 924322 (C4 (Web Text))

Max Activating Token Index: 375

Text #7

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0683. Min Act: -0.0000

Data Index: 729698 (C4 (Web Text))

Max Activating Token Index: 948

Text #8

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0699. Min Act: -0.0000

Data Index: 516476 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0623. Min Act: -0.0001

Data Index: 730994 (C4 (Web Text))

Max Activating Token Index: 815

Text #10

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0608. Min Act: -0.0001

Data Index: 1089310 (C4 (Web Text))

Max Activating Token Index: 322

Text #11

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0652. Min Act: -0.0000

Data Index: 87476 (C4 (Web Text))

Max Activating Token Index: 607

Text #12

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0627. Min Act: -0.0001

Data Index: 108892 (C4 (Web Text))

Max Activating Token Index: 500

Text #13

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0644. Min Act: -0.0001

Data Index: 1286763 (C4 (Web Text))

Max Activating Token Index: 932

Text #14

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0588. Min Act: -0.0001

Data Index: 1572075 (Python Code)

Max Activating Token Index: 980

Text #15

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0614. Min Act: -0.0001

Data Index: 1102750 (C4 (Web Text))

Max Activating Token Index: 577

Text #16

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0592. Min Act: -0.0000

Data Index: 1136058 (C4 (Web Text))

Max Activating Token Index: 746

Text #17

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0588. Min Act: -0.0001

Data Index: 1632256 (Python Code)

Max Activating Token Index: 311

Text #18

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0611. Min Act: -0.0000

Data Index: 1228801 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0588. Min Act: -0.0001

Data Index: 905021 (C4 (Web Text))

Max Activating Token Index: 546