Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2739 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.7466. Min Act: -0.0001

Data Index: 483678 (The Pile)

Max Activating Token Index: 745

Text #1

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.7257. Min Act: -0.0000

Data Index: 990300 (The Pile)

Max Activating Token Index: 1006

Text #2

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.7196. Min Act: -0.0000

Data Index: 315473 (The Pile)

Max Activating Token Index: 29

Text #3

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.6866. Min Act: -0.0000

Data Index: 840071 (The Pile)

Max Activating Token Index: 862

Text #4

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.6536. Min Act: -0.0000

Data Index: 911589 (The Pile)

Max Activating Token Index: 826

Text #5

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.6279. Min Act: -0.0000

Data Index: 1845127 (The Pile)

Max Activating Token Index: 995

Text #6

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.6514. Min Act: -0.0000

Data Index: 1013705 (The Pile)

Max Activating Token Index: 541

Text #7

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.6416. Min Act: -0.0000

Data Index: 1957438 (The Pile)

Max Activating Token Index: 349

Text #8

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.6516. Min Act: -0.0001

Data Index: 634473 (The Pile)

Max Activating Token Index: 780

Text #9

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.6311. Min Act: -0.0000

Data Index: 1863263 (The Pile)

Max Activating Token Index: 700

Text #10

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.5926. Min Act: -0.0000

Data Index: 1719111 (The Pile)

Max Activating Token Index: 736

Text #11

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.6071. Min Act: -0.0000

Data Index: 1681661 (The Pile)

Max Activating Token Index: 526

Text #12

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.6076. Min Act: -0.0000

Data Index: 1968243 (The Pile)

Max Activating Token Index: 314

Text #13

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.5990. Min Act: -0.0000

Data Index: 776356 (The Pile)

Max Activating Token Index: 997

Text #14

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.5751. Min Act: -0.0000

Data Index: 1388807 (The Pile)

Max Activating Token Index: 823

Text #15

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.6096. Min Act: -0.0001

Data Index: 475661 (The Pile)

Max Activating Token Index: 585

Text #16

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.6094. Min Act: -0.0000

Data Index: 1103485 (The Pile)

Max Activating Token Index: 919

Text #17

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.5685. Min Act: -0.0000

Data Index: 1222285 (The Pile)

Max Activating Token Index: 119

Text #18

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.6197. Min Act: -0.0000

Data Index: 1496551 (The Pile)

Max Activating Token Index: 879

Text #19

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.5826. Min Act: -0.0000

Data Index: 589675 (The Pile)

Max Activating Token Index: 837