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

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

Neuron 2806 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: 0.0647. Min Range: -0.0647

Max Act: 0.0599. Min Act: -0.0002

Data Index: 344780 (C4 (Web Text))

Max Activating Token Index: 216

Text #1

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0639. Min Act: -0.0002

Data Index: 1169974 (C4 (Web Text))

Max Activating Token Index: 216

Text #2

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0646. Min Act: -0.0002

Data Index: 713226 (C4 (Web Text))

Max Activating Token Index: 741

Text #3

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0629. Min Act: -0.0002

Data Index: 1293840 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0596. Min Act: -0.0002

Data Index: 310524 (C4 (Web Text))

Max Activating Token Index: 135

Text #5

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0631. Min Act: -0.0002

Data Index: 1050018 (C4 (Web Text))

Max Activating Token Index: 561

Text #6

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0614. Min Act: -0.0002

Data Index: 137547 (C4 (Web Text))

Max Activating Token Index: 942

Text #7

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0620. Min Act: -0.0002

Data Index: 473301 (C4 (Web Text))

Max Activating Token Index: 159

Text #8

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0556. Min Act: -0.0002

Data Index: 315751 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0644. Min Act: -0.0002

Data Index: 66565 (C4 (Web Text))

Max Activating Token Index: 95

Text #10

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0647. Min Act: -0.0002

Data Index: 463527 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0531. Min Act: -0.0002

Data Index: 1002084 (C4 (Web Text))

Max Activating Token Index: 112

Text #12

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0581. Min Act: -0.0002

Data Index: 82839 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0562. Min Act: -0.0002

Data Index: 887013 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0588. Min Act: -0.0002

Data Index: 13279 (C4 (Web Text))

Max Activating Token Index: 326

Text #15

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0493. Min Act: -0.0002

Data Index: 198709 (C4 (Web Text))

Max Activating Token Index: 157

Text #16

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0527. Min Act: -0.0002

Data Index: 1328504 (C4 (Web Text))

Max Activating Token Index: 536

Text #17

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0577. Min Act: -0.0002

Data Index: 505227 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0602. Min Act: -0.0002

Data Index: 28786 (C4 (Web Text))

Max Activating Token Index: 100

Text #19

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0563. Min Act: -0.0002

Data Index: 1172019 (C4 (Web Text))

Max Activating Token Index: 853