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

Dataset: The Pile

Neuron 273 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: 0.7624. Min Range: -0.7624

Max Act: 0.7624. Min Act: -0.0000

Data Index: 764523 (The Pile)

Max Activating Token Index: 752

Text #1

Max Range: 0.7624. Min Range: -0.7624

Max Act: 0.6552. Min Act: -0.0000

Data Index: 1317523 (The Pile)

Max Activating Token Index: 497

Text #2

Max Range: 0.7624. Min Range: -0.7624

Max Act: 0.6654. Min Act: -0.0000

Data Index: 842383 (The Pile)

Max Activating Token Index: 284

Text #3

Max Range: 0.7624. Min Range: -0.7624

Max Act: 0.7054. Min Act: -0.0000

Data Index: 513258 (The Pile)

Max Activating Token Index: 720

Text #4

Max Range: 0.7624. Min Range: -0.7624

Max Act: 0.6412. Min Act: -0.0000

Data Index: 883054 (The Pile)

Max Activating Token Index: 428

Text #5

Max Range: 0.7624. Min Range: -0.7624

Max Act: 0.6324. Min Act: -0.0000

Data Index: 1009553 (The Pile)

Max Activating Token Index: 818

Text #6

Max Range: 0.7624. Min Range: -0.7624

Max Act: 0.5598. Min Act: -0.0000

Data Index: 385056 (The Pile)

Max Activating Token Index: 553

Text #7

Max Range: 0.7624. Min Range: -0.7624

Max Act: 0.6252. Min Act: -0.0000

Data Index: 1278599 (The Pile)

Max Activating Token Index: 200

Text #8

Max Range: 0.7624. Min Range: -0.7624

Max Act: 0.6206. Min Act: -0.0000

Data Index: 1004065 (The Pile)

Max Activating Token Index: 793

Text #9

Max Range: 0.7624. Min Range: -0.7624

Max Act: 0.5550. Min Act: -0.0000

Data Index: 1906309 (The Pile)

Max Activating Token Index: 135

Text #10

Max Range: 0.7624. Min Range: -0.7624

Max Act: 0.6187. Min Act: -0.0000

Data Index: 498669 (The Pile)

Max Activating Token Index: 831

Text #11

Max Range: 0.7624. Min Range: -0.7624

Max Act: 0.5612. Min Act: -0.0000

Data Index: 1848516 (The Pile)

Max Activating Token Index: 744

Text #12

Max Range: 0.7624. Min Range: -0.7624

Max Act: 0.6514. Min Act: -0.0000

Data Index: 394262 (The Pile)

Max Activating Token Index: 781

Text #13

Max Range: 0.7624. Min Range: -0.7624

Max Act: 0.5558. Min Act: -0.0000

Data Index: 1386606 (The Pile)

Max Activating Token Index: 328

Text #14

Max Range: 0.7624. Min Range: -0.7624

Max Act: 0.5847. Min Act: -0.0000

Data Index: 367215 (The Pile)

Max Activating Token Index: 663

Text #15

Max Range: 0.7624. Min Range: -0.7624

Max Act: 0.5619. Min Act: -0.0000

Data Index: 834154 (The Pile)

Max Activating Token Index: 96

Text #16

Max Range: 0.7624. Min Range: -0.7624

Max Act: 0.5619. Min Act: -0.0000

Data Index: 1109979 (The Pile)

Max Activating Token Index: 96

Text #17

Max Range: 0.7624. Min Range: -0.7624

Max Act: 0.5493. Min Act: -0.0000

Data Index: 868930 (The Pile)

Max Activating Token Index: 142

Text #18

Max Range: 0.7624. Min Range: -0.7624

Max Act: 0.5767. Min Act: -0.0000

Data Index: 1067171 (The Pile)

Max Activating Token Index: 434

Text #19

Max Range: 0.7624. Min Range: -0.7624

Max Act: 0.5798. Min Act: -0.0000

Data Index: 1779644 (The Pile)

Max Activating Token Index: 933