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

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

Neuron 3521 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.3000. Min Act: -0.0002

Data Index: 6275 (C4 (Web Text))

Max Activating Token Index: 259

Text #1

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.2979. Min Act: -0.0002

Data Index: 1605552 (Python Code)

Max Activating Token Index: 312

Text #2

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.2961. Min Act: -0.0003

Data Index: 326294 (C4 (Web Text))

Max Activating Token Index: 609

Text #3

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.2953. Min Act: -0.0003

Data Index: 481478 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.2913. Min Act: -0.0002

Data Index: 1606658 (Python Code)

Max Activating Token Index: 566

Text #5

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.2823. Min Act: -0.0002

Data Index: 672368 (C4 (Web Text))

Max Activating Token Index: 9

Text #6

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.2738. Min Act: -0.0003

Data Index: 327227 (C4 (Web Text))

Max Activating Token Index: 627

Text #7

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.2748. Min Act: -0.0002

Data Index: 1548755 (Python Code)

Max Activating Token Index: 331

Text #8

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.2695. Min Act: -0.0003

Data Index: 534525 (C4 (Web Text))

Max Activating Token Index: 591

Text #9

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.2734. Min Act: -0.0003

Data Index: 811132 (C4 (Web Text))

Max Activating Token Index: 744

Text #10

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.2689. Min Act: -0.0003

Data Index: 239909 (C4 (Web Text))

Max Activating Token Index: 393

Text #11

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.2690. Min Act: -0.0002

Data Index: 45212 (C4 (Web Text))

Max Activating Token Index: 651

Text #12

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.2686. Min Act: -0.0002

Data Index: 155277 (C4 (Web Text))

Max Activating Token Index: 427

Text #13

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.2615. Min Act: -0.0002

Data Index: 1392001 (Python Code)

Max Activating Token Index: 402

Text #14

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.2700. Min Act: -0.0003

Data Index: 486246 (C4 (Web Text))

Max Activating Token Index: 572

Text #15

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.2651. Min Act: -0.0002

Data Index: 1565856 (Python Code)

Max Activating Token Index: 551

Text #16

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.2655. Min Act: -0.0002

Data Index: 793970 (C4 (Web Text))

Max Activating Token Index: 867

Text #17

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.2644. Min Act: -0.0003

Data Index: 925712 (C4 (Web Text))

Max Activating Token Index: 549

Text #18

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.2542. Min Act: -0.0003

Data Index: 9220 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.2627. Min Act: -0.0003

Data Index: 44450 (C4 (Web Text))

Max Activating Token Index: 516