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

Dataset: The Pile

Neuron 1773 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.3775. Min Act: -0.0000

Data Index: 323817 (The Pile)

Max Activating Token Index: 746

Text #1

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.3026. Min Act: -0.0000

Data Index: 305115 (The Pile)

Max Activating Token Index: 965

Text #2

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2624. Min Act: -0.0000

Data Index: 121983 (The Pile)

Max Activating Token Index: 534

Text #3

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2611. Min Act: -0.0000

Data Index: 649135 (The Pile)

Max Activating Token Index: 128

Text #4

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2529. Min Act: -0.0000

Data Index: 1938547 (The Pile)

Max Activating Token Index: 643

Text #5

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2615. Min Act: -0.0000

Data Index: 137361 (The Pile)

Max Activating Token Index: 228

Text #6

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2605. Min Act: -0.0000

Data Index: 1105105 (The Pile)

Max Activating Token Index: 336

Text #7

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2510. Min Act: -0.0000

Data Index: 737314 (The Pile)

Max Activating Token Index: 444

Text #8

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2324. Min Act: -0.0000

Data Index: 1289186 (The Pile)

Max Activating Token Index: 102

Text #9

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2597. Min Act: -0.0000

Data Index: 1125748 (The Pile)

Max Activating Token Index: 750

Text #10

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2345. Min Act: -0.0000

Data Index: 749226 (The Pile)

Max Activating Token Index: 608

Text #11

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2305. Min Act: -0.0000

Data Index: 1574709 (The Pile)

Max Activating Token Index: 549

Text #12

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2417. Min Act: -0.0000

Data Index: 213100 (The Pile)

Max Activating Token Index: 776

Text #13

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2257. Min Act: -0.0000

Data Index: 1074262 (The Pile)

Max Activating Token Index: 602

Text #14

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2456. Min Act: -0.0000

Data Index: 437421 (The Pile)

Max Activating Token Index: 720

Text #15

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2221. Min Act: -0.0000

Data Index: 670872 (The Pile)

Max Activating Token Index: 677

Text #16

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2327. Min Act: -0.0000

Data Index: 1392826 (The Pile)

Max Activating Token Index: 334

Text #17

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2308. Min Act: -0.0000

Data Index: 861302 (The Pile)

Max Activating Token Index: 701

Text #18

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2284. Min Act: -0.0000

Data Index: 348978 (The Pile)

Max Activating Token Index: 677

Text #19

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2285. Min Act: -0.0000

Data Index: 27853 (The Pile)

Max Activating Token Index: 130