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

Dataset: The Pile

Neuron 2295 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7702. Min Range: -1.7702

Max Act: 1.7702. Min Act: -0.0000

Data Index: 1574145 (The Pile)

Max Activating Token Index: 780

Text #1

Max Range: 1.7702. Min Range: -1.7702

Max Act: 1.5807. Min Act: -0.0000

Data Index: 297241 (The Pile)

Max Activating Token Index: 920

Text #2

Max Range: 1.7702. Min Range: -1.7702

Max Act: 1.5979. Min Act: -0.0000

Data Index: 710216 (The Pile)

Max Activating Token Index: 990

Text #3

Max Range: 1.7702. Min Range: -1.7702

Max Act: 1.5516. Min Act: -0.0000

Data Index: 1704668 (The Pile)

Max Activating Token Index: 286

Text #4

Max Range: 1.7702. Min Range: -1.7702

Max Act: 1.5349. Min Act: -0.0000

Data Index: 142514 (The Pile)

Max Activating Token Index: 383

Text #5

Max Range: 1.7702. Min Range: -1.7702

Max Act: 1.4245. Min Act: -0.0000

Data Index: 1549447 (The Pile)

Max Activating Token Index: 700

Text #6

Max Range: 1.7702. Min Range: -1.7702

Max Act: 1.4102. Min Act: -0.0000

Data Index: 1341829 (The Pile)

Max Activating Token Index: 367

Text #7

Max Range: 1.7702. Min Range: -1.7702

Max Act: 1.5792. Min Act: -0.0000

Data Index: 883436 (The Pile)

Max Activating Token Index: 774

Text #8

Max Range: 1.7702. Min Range: -1.7702

Max Act: 1.4652. Min Act: -0.0000

Data Index: 1755087 (The Pile)

Max Activating Token Index: 625

Text #9

Max Range: 1.7702. Min Range: -1.7702

Max Act: 1.5617. Min Act: -0.0000

Data Index: 1992476 (The Pile)

Max Activating Token Index: 647

Text #10

Max Range: 1.7702. Min Range: -1.7702

Max Act: 1.3281. Min Act: -0.0000

Data Index: 333383 (The Pile)

Max Activating Token Index: 828

Text #11

Max Range: 1.7702. Min Range: -1.7702

Max Act: 1.4720. Min Act: -0.0000

Data Index: 1582403 (The Pile)

Max Activating Token Index: 499

Text #12

Max Range: 1.7702. Min Range: -1.7702

Max Act: 1.2876. Min Act: -0.0000

Data Index: 1352392 (The Pile)

Max Activating Token Index: 442

Text #13

Max Range: 1.7702. Min Range: -1.7702

Max Act: 1.3344. Min Act: -0.0000

Data Index: 134985 (The Pile)

Max Activating Token Index: 290

Text #14

Max Range: 1.7702. Min Range: -1.7702

Max Act: 1.4458. Min Act: -0.0000

Data Index: 563681 (The Pile)

Max Activating Token Index: 747

Text #15

Max Range: 1.7702. Min Range: -1.7702

Max Act: 1.3234. Min Act: -0.0000

Data Index: 1132219 (The Pile)

Max Activating Token Index: 779

Text #16

Max Range: 1.7702. Min Range: -1.7702

Max Act: 1.3085. Min Act: -0.0000

Data Index: 1807894 (The Pile)

Max Activating Token Index: 251

Text #17

Max Range: 1.7702. Min Range: -1.7702

Max Act: 1.3901. Min Act: -0.0000

Data Index: 1755439 (The Pile)

Max Activating Token Index: 865

Text #18

Max Range: 1.7702. Min Range: -1.7702

Max Act: 1.4480. Min Act: -0.0000

Data Index: 964420 (The Pile)

Max Activating Token Index: 951

Text #19

Max Range: 1.7702. Min Range: -1.7702

Max Act: 1.3937. Min Act: -0.0000

Data Index: 1310120 (The Pile)

Max Activating Token Index: 678