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

Dataset: The Pile

Neuron 4741 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3745. Min Range: -3.3745

Max Act: 3.1393. Min Act: -0.0000

Data Index: 380375 (The Pile)

Max Activating Token Index: 807

Text #1

Max Range: 3.3745. Min Range: -3.3745

Max Act: 3.3745. Min Act: -0.0000

Data Index: 1293055 (The Pile)

Max Activating Token Index: 686

Text #2

Max Range: 3.3745. Min Range: -3.3745

Max Act: 2.9148. Min Act: -0.0000

Data Index: 1619085 (The Pile)

Max Activating Token Index: 709

Text #3

Max Range: 3.3745. Min Range: -3.3745

Max Act: 3.3097. Min Act: -0.0000

Data Index: 1215774 (The Pile)

Max Activating Token Index: 664

Text #4

Max Range: 3.3745. Min Range: -3.3745

Max Act: 3.3608. Min Act: -0.0000

Data Index: 382703 (The Pile)

Max Activating Token Index: 841

Text #5

Max Range: 3.3745. Min Range: -3.3745

Max Act: 2.8074. Min Act: -0.0000

Data Index: 692184 (The Pile)

Max Activating Token Index: 459

Text #6

Max Range: 3.3745. Min Range: -3.3745

Max Act: 2.7809. Min Act: -0.0000

Data Index: 1085455 (The Pile)

Max Activating Token Index: 584

Text #7

Max Range: 3.3745. Min Range: -3.3745

Max Act: 2.0386. Min Act: -0.0000

Data Index: 605166 (The Pile)

Max Activating Token Index: 488

Text #8

Max Range: 3.3745. Min Range: -3.3745

Max Act: 1.8703. Min Act: -0.0000

Data Index: 837125 (The Pile)

Max Activating Token Index: 939

Text #9

Max Range: 3.3745. Min Range: -3.3745

Max Act: 2.3254. Min Act: -0.0000

Data Index: 1286007 (The Pile)

Max Activating Token Index: 841

Text #10

Max Range: 3.3745. Min Range: -3.3745

Max Act: 2.5226. Min Act: -0.0000

Data Index: 221325 (The Pile)

Max Activating Token Index: 714

Text #11

Max Range: 3.3745. Min Range: -3.3745

Max Act: 2.4587. Min Act: -0.0000

Data Index: 186615 (The Pile)

Max Activating Token Index: 646

Text #12

Max Range: 3.3745. Min Range: -3.3745

Max Act: 1.9800. Min Act: -0.0000

Data Index: 91555 (The Pile)

Max Activating Token Index: 655

Text #13

Max Range: 3.3745. Min Range: -3.3745

Max Act: 2.4603. Min Act: -0.0000

Data Index: 484755 (The Pile)

Max Activating Token Index: 878

Text #14

Max Range: 3.3745. Min Range: -3.3745

Max Act: 2.2862. Min Act: -0.0000

Data Index: 1234234 (The Pile)

Max Activating Token Index: 108

Text #15

Max Range: 3.3745. Min Range: -3.3745

Max Act: 2.2288. Min Act: -0.0000

Data Index: 1620892 (The Pile)

Max Activating Token Index: 403

Text #16

Max Range: 3.3745. Min Range: -3.3745

Max Act: 1.8342. Min Act: -0.0000

Data Index: 624304 (The Pile)

Max Activating Token Index: 631

Text #17

Max Range: 3.3745. Min Range: -3.3745

Max Act: 2.3076. Min Act: -0.0000

Data Index: 1324830 (The Pile)

Max Activating Token Index: 77

Text #18

Max Range: 3.3745. Min Range: -3.3745

Max Act: 1.9025. Min Act: -0.0000

Data Index: 184339 (The Pile)

Max Activating Token Index: 281

Text #19

Max Range: 3.3745. Min Range: -3.3745

Max Act: 1.9780. Min Act: -0.0000

Data Index: 1503340 (The Pile)

Max Activating Token Index: 319