Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1618 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.3571. Min Act: -0.0000

Data Index: 508248 (The Pile)

Max Activating Token Index: 715

Text #1

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.3299. Min Act: -0.0000

Data Index: 284100 (The Pile)

Max Activating Token Index: 95

Text #2

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.3065. Min Act: -0.0000

Data Index: 1635844 (The Pile)

Max Activating Token Index: 240

Text #3

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2975. Min Act: -0.0000

Data Index: 672054 (The Pile)

Max Activating Token Index: 413

Text #4

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.3108. Min Act: -0.0000

Data Index: 882450 (The Pile)

Max Activating Token Index: 62

Text #5

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2886. Min Act: -0.0000

Data Index: 1509734 (The Pile)

Max Activating Token Index: 156

Text #6

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2931. Min Act: -0.0000

Data Index: 561927 (The Pile)

Max Activating Token Index: 748

Text #7

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2689. Min Act: -0.0000

Data Index: 163152 (The Pile)

Max Activating Token Index: 428

Text #8

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2834. Min Act: -0.0000

Data Index: 1931794 (The Pile)

Max Activating Token Index: 68

Text #9

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2662. Min Act: -0.0000

Data Index: 940806 (The Pile)

Max Activating Token Index: 662

Text #10

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2750. Min Act: -0.0000

Data Index: 787908 (The Pile)

Max Activating Token Index: 776

Text #11

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2550. Min Act: -0.0000

Data Index: 194279 (The Pile)

Max Activating Token Index: 674

Text #12

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2565. Min Act: -0.0000

Data Index: 1828911 (The Pile)

Max Activating Token Index: 146

Text #13

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2649. Min Act: -0.0000

Data Index: 1825855 (The Pile)

Max Activating Token Index: 43

Text #14

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2584. Min Act: -0.0000

Data Index: 1723780 (The Pile)

Max Activating Token Index: 358

Text #15

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2789. Min Act: -0.0000

Data Index: 1977146 (The Pile)

Max Activating Token Index: 770

Text #16

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2483. Min Act: -0.0000

Data Index: 598551 (The Pile)

Max Activating Token Index: 544

Text #17

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2438. Min Act: -0.0000

Data Index: 282340 (The Pile)

Max Activating Token Index: 268

Text #18

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2503. Min Act: -0.0000

Data Index: 1353644 (The Pile)

Max Activating Token Index: 393

Text #19

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2601. Min Act: -0.0000

Data Index: 761502 (The Pile)

Max Activating Token Index: 481