Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 616 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0634. Min Act: -0.0002

Data Index: 130980 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0602. Min Act: -0.0002

Data Index: 943651 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0599. Min Act: -0.0002

Data Index: 878286 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0588. Min Act: -0.0002

Data Index: 331998 (C4 (Web Text))

Max Activating Token Index: 154

Text #4

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0586. Min Act: -0.0002

Data Index: 703237 (C4 (Web Text))

Max Activating Token Index: 333

Text #5

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0583. Min Act: -0.0002

Data Index: 381321 (C4 (Web Text))

Max Activating Token Index: 434

Text #6

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0563. Min Act: -0.0002

Data Index: 354277 (C4 (Web Text))

Max Activating Token Index: 824

Text #7

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0591. Min Act: -0.0002

Data Index: 1239569 (C4 (Web Text))

Max Activating Token Index: 662

Text #8

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0571. Min Act: -0.0002

Data Index: 729616 (C4 (Web Text))

Max Activating Token Index: 395

Text #9

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0568. Min Act: -0.0002

Data Index: 9263 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0594. Min Act: -0.0002

Data Index: 1075570 (C4 (Web Text))

Max Activating Token Index: 913

Text #11

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0555. Min Act: -0.0002

Data Index: 315850 (C4 (Web Text))

Max Activating Token Index: 272

Text #12

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0557. Min Act: -0.0002

Data Index: 1159632 (C4 (Web Text))

Max Activating Token Index: 391

Text #13

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0563. Min Act: -0.0002

Data Index: 855055 (C4 (Web Text))

Max Activating Token Index: 316

Text #14

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0543. Min Act: -0.0002

Data Index: 137171 (C4 (Web Text))

Max Activating Token Index: 234

Text #15

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0555. Min Act: -0.0002

Data Index: 365874 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0555. Min Act: -0.0002

Data Index: 509960 (C4 (Web Text))

Max Activating Token Index: 324

Text #17

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0500. Min Act: -0.0002

Data Index: 273874 (C4 (Web Text))

Max Activating Token Index: 642

Text #18

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0527. Min Act: -0.0002

Data Index: 582129 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0549. Min Act: -0.0002

Data Index: 190605 (C4 (Web Text))

Max Activating Token Index: 780