Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1232 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0646. Min Act: -0.0003

Data Index: 1065530 (C4 (Web Text))

Max Activating Token Index: 198

Text #1

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0660. Min Act: -0.0003

Data Index: 58518 (C4 (Web Text))

Max Activating Token Index: 690

Text #2

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0641. Min Act: -0.0003

Data Index: 1252172 (C4 (Web Text))

Max Activating Token Index: 520

Text #3

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0628. Min Act: -0.0003

Data Index: 65382 (C4 (Web Text))

Max Activating Token Index: 453

Text #4

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0616. Min Act: -0.0003

Data Index: 567812 (C4 (Web Text))

Max Activating Token Index: 529

Text #5

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0634. Min Act: -0.0003

Data Index: 335654 (C4 (Web Text))

Max Activating Token Index: 957

Text #6

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0584. Min Act: -0.0003

Data Index: 106151 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0587. Min Act: -0.0004

Data Index: 924524 (C4 (Web Text))

Max Activating Token Index: 548

Text #8

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0579. Min Act: -0.0003

Data Index: 7862 (C4 (Web Text))

Max Activating Token Index: 755

Text #9

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0575. Min Act: -0.0003

Data Index: 929030 (C4 (Web Text))

Max Activating Token Index: 984

Text #10

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0556. Min Act: -0.0003

Data Index: 1307596 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0569. Min Act: -0.0003

Data Index: 867627 (C4 (Web Text))

Max Activating Token Index: 373

Text #12

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0519. Min Act: -0.0003

Data Index: 1031441 (C4 (Web Text))

Max Activating Token Index: 716

Text #13

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0546. Min Act: -0.0003

Data Index: 863854 (C4 (Web Text))

Max Activating Token Index: 478

Text #14

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0527. Min Act: -0.0003

Data Index: 145547 (C4 (Web Text))

Max Activating Token Index: 671

Text #15

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0545. Min Act: -0.0002

Data Index: 732038 (C4 (Web Text))

Max Activating Token Index: 655

Text #16

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0528. Min Act: -0.0003

Data Index: 806617 (C4 (Web Text))

Max Activating Token Index: 194

Text #17

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0534. Min Act: -0.0002

Data Index: 426494 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0543. Min Act: -0.0002

Data Index: 735527 (C4 (Web Text))

Max Activating Token Index: 168

Text #19

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0538. Min Act: -0.0003

Data Index: 1321153 (C4 (Web Text))

Max Activating Token Index: 155