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

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

Neuron 3078 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0635. Min Act: -0.0000

Data Index: 1028550 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0592. Min Act: -0.0000

Data Index: 965365 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0619. Min Act: -0.0000

Data Index: 490819 (C4 (Web Text))

Max Activating Token Index: 832

Text #3

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0598. Min Act: -0.0000

Data Index: 783987 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0577. Min Act: -0.0000

Data Index: 46520 (C4 (Web Text))

Max Activating Token Index: 114

Text #5

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0596. Min Act: -0.0000

Data Index: 627930 (C4 (Web Text))

Max Activating Token Index: 476

Text #6

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0594. Min Act: -0.0000

Data Index: 629994 (C4 (Web Text))

Max Activating Token Index: 871

Text #7

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0613. Min Act: -0.0000

Data Index: 927481 (C4 (Web Text))

Max Activating Token Index: 673

Text #8

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0563. Min Act: -0.0000

Data Index: 63749 (C4 (Web Text))

Max Activating Token Index: 962

Text #9

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0571. Min Act: -0.0000

Data Index: 852984 (C4 (Web Text))

Max Activating Token Index: 82

Text #10

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0550. Min Act: -0.0000

Data Index: 1300561 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0528. Min Act: -0.0000

Data Index: 105350 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0558. Min Act: -0.0000

Data Index: 1053533 (C4 (Web Text))

Max Activating Token Index: 997

Text #13

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0549. Min Act: -0.0000

Data Index: 970890 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0528. Min Act: -0.0000

Data Index: 1100329 (C4 (Web Text))

Max Activating Token Index: 762

Text #15

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0520. Min Act: -0.0000

Data Index: 751543 (C4 (Web Text))

Max Activating Token Index: 737

Text #16

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0538. Min Act: -0.0000

Data Index: 154960 (C4 (Web Text))

Max Activating Token Index: 480

Text #17

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0531. Min Act: -0.0000

Data Index: 467022 (C4 (Web Text))

Max Activating Token Index: 678

Text #18

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0531. Min Act: -0.0000

Data Index: 365725 (C4 (Web Text))

Max Activating Token Index: 106

Text #19

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0551. Min Act: -0.0000

Data Index: 175309 (C4 (Web Text))

Max Activating Token Index: 840