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

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

Neuron 868 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: 0.0611. Min Range: -0.0611

Max Act: 0.0601. Min Act: -0.0003

Data Index: 1121871 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0611. Min Act: -0.0002

Data Index: 458351 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0605. Min Act: -0.0002

Data Index: 171866 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0600. Min Act: -0.0002

Data Index: 884032 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0580. Min Act: -0.0000

Data Index: 484806 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0556. Min Act: -0.0000

Data Index: 1264877 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0573. Min Act: -0.0003

Data Index: 281785 (C4 (Web Text))

Max Activating Token Index: 244

Text #7

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0555. Min Act: -0.0003

Data Index: 891577 (C4 (Web Text))

Max Activating Token Index: 867

Text #8

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0558. Min Act: -0.0002

Data Index: 311697 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0545. Min Act: -0.0002

Data Index: 1044909 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0548. Min Act: -0.0002

Data Index: 1308259 (C4 (Web Text))

Max Activating Token Index: 532

Text #11

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0545. Min Act: -0.0002

Data Index: 1257988 (C4 (Web Text))

Max Activating Token Index: 734

Text #12

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0552. Min Act: -0.0000

Data Index: 404945 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0535. Min Act: -0.0000

Data Index: 646766 (C4 (Web Text))

Max Activating Token Index: 377

Text #14

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0542. Min Act: -0.0002

Data Index: 545339 (C4 (Web Text))

Max Activating Token Index: 508

Text #15

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0534. Min Act: -0.0003

Data Index: 430154 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0530. Min Act: -0.0000

Data Index: 496669 (C4 (Web Text))

Max Activating Token Index: 120

Text #17

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0530. Min Act: -0.0002

Data Index: 794398 (C4 (Web Text))

Max Activating Token Index: 338

Text #18

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0535. Min Act: -0.0002

Data Index: 842863 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0526. Min Act: -0.0000

Data Index: 859230 (C4 (Web Text))

Max Activating Token Index: 78