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

Dataset: The Pile

Neuron 483 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3349. Min Range: -3.3349

Max Act: 3.3349. Min Act: -0.0000

Data Index: 1871022 (The Pile)

Max Activating Token Index: 523

Text #1

Max Range: 3.3349. Min Range: -3.3349

Max Act: 3.0975. Min Act: -0.0000

Data Index: 1163687 (The Pile)

Max Activating Token Index: 481

Text #2

Max Range: 3.3349. Min Range: -3.3349

Max Act: 2.7897. Min Act: -0.0000

Data Index: 1319340 (The Pile)

Max Activating Token Index: 594

Text #3

Max Range: 3.3349. Min Range: -3.3349

Max Act: 2.8776. Min Act: -0.0000

Data Index: 1334749 (The Pile)

Max Activating Token Index: 958

Text #4

Max Range: 3.3349. Min Range: -3.3349

Max Act: 2.6785. Min Act: -0.0000

Data Index: 974704 (The Pile)

Max Activating Token Index: 88

Text #5

Max Range: 3.3349. Min Range: -3.3349

Max Act: 2.6802. Min Act: -0.0000

Data Index: 310679 (The Pile)

Max Activating Token Index: 696

Text #6

Max Range: 3.3349. Min Range: -3.3349

Max Act: 2.6676. Min Act: -0.0000

Data Index: 442165 (The Pile)

Max Activating Token Index: 756

Text #7

Max Range: 3.3349. Min Range: -3.3349

Max Act: 2.6653. Min Act: -0.0000

Data Index: 74422 (The Pile)

Max Activating Token Index: 456

Text #8

Max Range: 3.3349. Min Range: -3.3349

Max Act: 2.5710. Min Act: -0.0000

Data Index: 825980 (The Pile)

Max Activating Token Index: 869

Text #9

Max Range: 3.3349. Min Range: -3.3349

Max Act: 2.6992. Min Act: -0.0000

Data Index: 985872 (The Pile)

Max Activating Token Index: 99

Text #10

Max Range: 3.3349. Min Range: -3.3349

Max Act: 2.4378. Min Act: -0.0000

Data Index: 295590 (The Pile)

Max Activating Token Index: 325

Text #11

Max Range: 3.3349. Min Range: -3.3349

Max Act: 2.6796. Min Act: -0.0000

Data Index: 1676644 (The Pile)

Max Activating Token Index: 522

Text #12

Max Range: 3.3349. Min Range: -3.3349

Max Act: 2.5436. Min Act: -0.0000

Data Index: 313080 (The Pile)

Max Activating Token Index: 875

Text #13

Max Range: 3.3349. Min Range: -3.3349

Max Act: 2.3806. Min Act: -0.0000

Data Index: 1380470 (The Pile)

Max Activating Token Index: 979

Text #14

Max Range: 3.3349. Min Range: -3.3349

Max Act: 2.4744. Min Act: -0.0000

Data Index: 362708 (The Pile)

Max Activating Token Index: 787

Text #15

Max Range: 3.3349. Min Range: -3.3349

Max Act: 2.3387. Min Act: -0.0000

Data Index: 1008556 (The Pile)

Max Activating Token Index: 479

Text #16

Max Range: 3.3349. Min Range: -3.3349

Max Act: 2.4099. Min Act: -0.0000

Data Index: 705339 (The Pile)

Max Activating Token Index: 537

Text #17

Max Range: 3.3349. Min Range: -3.3349

Max Act: 2.4105. Min Act: -0.0000

Data Index: 139085 (The Pile)

Max Activating Token Index: 22

Text #18

Max Range: 3.3349. Min Range: -3.3349

Max Act: 2.2630. Min Act: -0.0000

Data Index: 1828185 (The Pile)

Max Activating Token Index: 958

Text #19

Max Range: 3.3349. Min Range: -3.3349

Max Act: 2.2601. Min Act: -0.0000

Data Index: 466374 (The Pile)

Max Activating Token Index: 119