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

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

Neuron 3514 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: 0.0682. Min Range: -0.0682

Max Act: 0.0682. Min Act: -0.0001

Data Index: 763418 (C4 (Web Text))

Max Activating Token Index: 561

Text #1

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0680. Min Act: -0.0001

Data Index: 233923 (C4 (Web Text))

Max Activating Token Index: 571

Text #2

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0613. Min Act: -0.0002

Data Index: 459391 (C4 (Web Text))

Max Activating Token Index: 284

Text #3

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0662. Min Act: -0.0001

Data Index: 774957 (C4 (Web Text))

Max Activating Token Index: 562

Text #4

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0669. Min Act: -0.0001

Data Index: 1589407 (Python Code)

Max Activating Token Index: 496

Text #5

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0664. Min Act: -0.0001

Data Index: 112788 (C4 (Web Text))

Max Activating Token Index: 784

Text #6

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0631. Min Act: -0.0001

Data Index: 513763 (C4 (Web Text))

Max Activating Token Index: 339

Text #7

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0629. Min Act: -0.0002

Data Index: 1309919 (C4 (Web Text))

Max Activating Token Index: 329

Text #8

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0579. Min Act: -0.0002

Data Index: 721819 (C4 (Web Text))

Max Activating Token Index: 631

Text #9

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0627. Min Act: -0.0002

Data Index: 292941 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0613. Min Act: -0.0002

Data Index: 635087 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0571. Min Act: -0.0002

Data Index: 359965 (C4 (Web Text))

Max Activating Token Index: 426

Text #12

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0553. Min Act: -0.0002

Data Index: 1296868 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0583. Min Act: -0.0001

Data Index: 889114 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0578. Min Act: -0.0002

Data Index: 308395 (C4 (Web Text))

Max Activating Token Index: 364

Text #15

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0552. Min Act: -0.0002

Data Index: 870428 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0554. Min Act: -0.0001

Data Index: 1100410 (C4 (Web Text))

Max Activating Token Index: 130

Text #17

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0532. Min Act: -0.0002

Data Index: 184752 (C4 (Web Text))

Max Activating Token Index: 553

Text #18

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0585. Min Act: -0.0002

Data Index: 288521 (C4 (Web Text))

Max Activating Token Index: 373

Text #19

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0565. Min Act: -0.0002

Data Index: 811822 (C4 (Web Text))

Max Activating Token Index: 383