Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 38 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.4710. Min Act: -0.0001

Data Index: 687044 (C4 (Web Text))

Max Activating Token Index: 537

Text #1

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.4627. Min Act: -0.0001

Data Index: 913793 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.4483. Min Act: -0.0001

Data Index: 404206 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.4024. Min Act: -0.0001

Data Index: 940614 (C4 (Web Text))

Max Activating Token Index: 586

Text #4

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3924. Min Act: -0.0001

Data Index: 923463 (C4 (Web Text))

Max Activating Token Index: 874

Text #5

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.4066. Min Act: -0.0001

Data Index: 48842 (C4 (Web Text))

Max Activating Token Index: 318

Text #6

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.4048. Min Act: -0.0001

Data Index: 604742 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3908. Min Act: -0.0000

Data Index: 1263296 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3880. Min Act: -0.0001

Data Index: 244920 (C4 (Web Text))

Max Activating Token Index: 237

Text #9

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3855. Min Act: -0.0001

Data Index: 1336765 (C4 (Web Text))

Max Activating Token Index: 766

Text #10

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3839. Min Act: -0.0001

Data Index: 745544 (C4 (Web Text))

Max Activating Token Index: 695

Text #11

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3806. Min Act: -0.0001

Data Index: 183371 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3781. Min Act: -0.0001

Data Index: 907045 (C4 (Web Text))

Max Activating Token Index: 377

Text #13

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3910. Min Act: -0.0001

Data Index: 1249778 (C4 (Web Text))

Max Activating Token Index: 499

Text #14

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3756. Min Act: -0.0001

Data Index: 271760 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3487. Min Act: -0.0001

Data Index: 1252340 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3579. Min Act: -0.0001

Data Index: 123662 (C4 (Web Text))

Max Activating Token Index: 779

Text #17

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3543. Min Act: -0.0000

Data Index: 829038 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3419. Min Act: -0.0001

Data Index: 680412 (C4 (Web Text))

Max Activating Token Index: 793

Text #19

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3531. Min Act: -0.0001

Data Index: 931987 (C4 (Web Text))

Max Activating Token Index: 705