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

Dataset: The Pile

Neuron 1066 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1704. Min Range: -1.1704

Max Act: 1.1704. Min Act: -0.0000

Data Index: 362427 (The Pile)

Max Activating Token Index: 440

Text #1

Max Range: 1.1704. Min Range: -1.1704

Max Act: 1.0348. Min Act: -0.0000

Data Index: 585523 (The Pile)

Max Activating Token Index: 541

Text #2

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.8110. Min Act: -0.0000

Data Index: 542775 (The Pile)

Max Activating Token Index: 673

Text #3

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.8207. Min Act: -0.0000

Data Index: 353953 (The Pile)

Max Activating Token Index: 120

Text #4

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.8081. Min Act: -0.0000

Data Index: 1904911 (The Pile)

Max Activating Token Index: 95

Text #5

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.6962. Min Act: -0.0000

Data Index: 778434 (The Pile)

Max Activating Token Index: 1011

Text #6

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.7361. Min Act: -0.0000

Data Index: 930927 (The Pile)

Max Activating Token Index: 156

Text #7

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.7267. Min Act: -0.0000

Data Index: 1669812 (The Pile)

Max Activating Token Index: 478

Text #8

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.7391. Min Act: -0.0000

Data Index: 1740567 (The Pile)

Max Activating Token Index: 401

Text #9

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.6653. Min Act: -0.0000

Data Index: 1702477 (The Pile)

Max Activating Token Index: 57

Text #10

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.6426. Min Act: -0.0000

Data Index: 198394 (The Pile)

Max Activating Token Index: 617

Text #11

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.5665. Min Act: -0.0000

Data Index: 1977067 (The Pile)

Max Activating Token Index: 742

Text #12

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.7659. Min Act: -0.0000

Data Index: 780210 (The Pile)

Max Activating Token Index: 94

Text #13

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.6323. Min Act: -0.0000

Data Index: 666727 (The Pile)

Max Activating Token Index: 379

Text #14

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.5819. Min Act: -0.0000

Data Index: 1731320 (The Pile)

Max Activating Token Index: 808

Text #15

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.6388. Min Act: -0.0000

Data Index: 1471169 (The Pile)

Max Activating Token Index: 343

Text #16

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.5544. Min Act: -0.0000

Data Index: 684056 (The Pile)

Max Activating Token Index: 295

Text #17

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.5634. Min Act: -0.0000

Data Index: 1883718 (The Pile)

Max Activating Token Index: 410

Text #18

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.5529. Min Act: -0.0000

Data Index: 1656390 (The Pile)

Max Activating Token Index: 707

Text #19

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.4179. Min Act: -0.0000

Data Index: 299264 (The Pile)

Max Activating Token Index: 867