Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 43 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0946. Min Act: -0.0001

Data Index: 785716 (C4 (Web Text))

Max Activating Token Index: 927

Text #1

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0770. Min Act: -0.0002

Data Index: 452744 (C4 (Web Text))

Max Activating Token Index: 393

Text #2

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0700. Min Act: -0.0002

Data Index: 940566 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0695. Min Act: -0.0002

Data Index: 612425 (C4 (Web Text))

Max Activating Token Index: 198

Text #4

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0634. Min Act: -0.0002

Data Index: 520756 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0642. Min Act: -0.0002

Data Index: 397702 (C4 (Web Text))

Max Activating Token Index: 279

Text #6

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0591. Min Act: -0.0002

Data Index: 1321813 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0546. Min Act: -0.0002

Data Index: 124326 (C4 (Web Text))

Max Activating Token Index: 358

Text #8

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0601. Min Act: -0.0002

Data Index: 1256609 (C4 (Web Text))

Max Activating Token Index: 333

Text #9

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0574. Min Act: -0.0002

Data Index: 223290 (C4 (Web Text))

Max Activating Token Index: 945

Text #10

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0540. Min Act: -0.0002

Data Index: 1142071 (C4 (Web Text))

Max Activating Token Index: 251

Text #11

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0599. Min Act: -0.0002

Data Index: 578501 (C4 (Web Text))

Max Activating Token Index: 915

Text #12

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0568. Min Act: -0.0002

Data Index: 34335 (C4 (Web Text))

Max Activating Token Index: 323

Text #13

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0606. Min Act: -0.0002

Data Index: 863449 (C4 (Web Text))

Max Activating Token Index: 313

Text #14

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0533. Min Act: -0.0001

Data Index: 1346141 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0553. Min Act: -0.0001

Data Index: 773977 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0561. Min Act: -0.0002

Data Index: 147875 (C4 (Web Text))

Max Activating Token Index: 983

Text #17

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0522. Min Act: -0.0001

Data Index: 1285268 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0532. Min Act: -0.0001

Data Index: 627741 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0550. Min Act: -0.0002

Data Index: 998745 (C4 (Web Text))

Max Activating Token Index: 92