Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1257 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0751. Min Act: -0.0003

Data Index: 385160 (C4 (Web Text))

Max Activating Token Index: 592

Text #1

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0711. Min Act: -0.0003

Data Index: 655614 (C4 (Web Text))

Max Activating Token Index: 694

Text #2

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0661. Min Act: -0.0002

Data Index: 1084837 (C4 (Web Text))

Max Activating Token Index: 518

Text #3

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0640. Min Act: -0.0003

Data Index: 831734 (C4 (Web Text))

Max Activating Token Index: 778

Text #4

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0626. Min Act: -0.0003

Data Index: 1019694 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0635. Min Act: -0.0003

Data Index: 895676 (C4 (Web Text))

Max Activating Token Index: 939

Text #6

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0610. Min Act: -0.0003

Data Index: 1170863 (C4 (Web Text))

Max Activating Token Index: 668

Text #7

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0610. Min Act: -0.0003

Data Index: 941884 (C4 (Web Text))

Max Activating Token Index: 263

Text #8

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0589. Min Act: -0.0003

Data Index: 618185 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0588. Min Act: -0.0003

Data Index: 1401546 (Python Code)

Max Activating Token Index: 319

Text #10

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0594. Min Act: -0.0003

Data Index: 1335185 (C4 (Web Text))

Max Activating Token Index: 1014

Text #11

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0586. Min Act: -0.0003

Data Index: 138418 (C4 (Web Text))

Max Activating Token Index: 543

Text #12

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0583. Min Act: -0.0003

Data Index: 981624 (C4 (Web Text))

Max Activating Token Index: 719

Text #13

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0581. Min Act: -0.0002

Data Index: 1377270 (Python Code)

Max Activating Token Index: 473

Text #14

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0591. Min Act: -0.0003

Data Index: 812489 (C4 (Web Text))

Max Activating Token Index: 1004

Text #15

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0589. Min Act: -0.0003

Data Index: 324086 (C4 (Web Text))

Max Activating Token Index: 953

Text #16

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0577. Min Act: -0.0003

Data Index: 762184 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0576. Min Act: -0.0003

Data Index: 325837 (C4 (Web Text))

Max Activating Token Index: 911

Text #18

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0577. Min Act: -0.0003

Data Index: 901271 (C4 (Web Text))

Max Activating Token Index: 822

Text #19

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0575. Min Act: -0.0003

Data Index: 1222555 (C4 (Web Text))

Max Activating Token Index: 526