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

Dataset: The Pile

Neuron 4512 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: 0.7680. Min Range: -0.7680

Max Act: 0.7667. Min Act: -0.0000

Data Index: 1445763 (The Pile)

Max Activating Token Index: 492

Text #1

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.7430. Min Act: -0.0000

Data Index: 1713342 (The Pile)

Max Activating Token Index: 499

Text #2

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.7680. Min Act: -0.0000

Data Index: 1350024 (The Pile)

Max Activating Token Index: 605

Text #3

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.7275. Min Act: 0.0000

Data Index: 929726 (The Pile)

Max Activating Token Index: 706

Text #4

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.6837. Min Act: -0.0000

Data Index: 1219384 (The Pile)

Max Activating Token Index: 652

Text #5

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.6689. Min Act: -0.0000

Data Index: 844691 (The Pile)

Max Activating Token Index: 134

Text #6

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.7183. Min Act: -0.0000

Data Index: 1847056 (The Pile)

Max Activating Token Index: 706

Text #7

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.6475. Min Act: -0.0000

Data Index: 346260 (The Pile)

Max Activating Token Index: 912

Text #8

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.6227. Min Act: -0.0000

Data Index: 985236 (The Pile)

Max Activating Token Index: 710

Text #9

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.6907. Min Act: -0.0000

Data Index: 54582 (The Pile)

Max Activating Token Index: 977

Text #10

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.5987. Min Act: -0.0000

Data Index: 1827949 (The Pile)

Max Activating Token Index: 898

Text #11

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.5543. Min Act: -0.0000

Data Index: 48804 (The Pile)

Max Activating Token Index: 1009

Text #12

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.6632. Min Act: -0.0000

Data Index: 1707750 (The Pile)

Max Activating Token Index: 511

Text #13

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.6079. Min Act: -0.0000

Data Index: 722020 (The Pile)

Max Activating Token Index: 257

Text #14

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.6022. Min Act: -0.0000

Data Index: 1236024 (The Pile)

Max Activating Token Index: 56

Text #15

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.5550. Min Act: -0.0000

Data Index: 168307 (The Pile)

Max Activating Token Index: 202

Text #16

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.5847. Min Act: -0.0000

Data Index: 1589677 (The Pile)

Max Activating Token Index: 397

Text #17

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.4849. Min Act: -0.0000

Data Index: 850042 (The Pile)

Max Activating Token Index: 58

Text #18

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.5836. Min Act: -0.0000

Data Index: 1780704 (The Pile)

Max Activating Token Index: 312

Text #19

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.6140. Min Act: -0.0000

Data Index: 1170010 (The Pile)

Max Activating Token Index: 170