Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1088 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.7684. Min Act: -0.0000

Data Index: 1374625 (The Pile)

Max Activating Token Index: 374

Text #1

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.5668. Min Act: -0.0000

Data Index: 500340 (The Pile)

Max Activating Token Index: 633

Text #2

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.5755. Min Act: -0.0000

Data Index: 1630971 (The Pile)

Max Activating Token Index: 459

Text #3

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.6240. Min Act: -0.0000

Data Index: 1652576 (The Pile)

Max Activating Token Index: 537

Text #4

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.5780. Min Act: -0.0000

Data Index: 531852 (The Pile)

Max Activating Token Index: 479

Text #5

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.5189. Min Act: -0.0000

Data Index: 429830 (The Pile)

Max Activating Token Index: 558

Text #6

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.5920. Min Act: -0.0000

Data Index: 1399160 (The Pile)

Max Activating Token Index: 644

Text #7

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.5219. Min Act: -0.0000

Data Index: 313207 (The Pile)

Max Activating Token Index: 605

Text #8

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.4608. Min Act: -0.0000

Data Index: 1724329 (The Pile)

Max Activating Token Index: 839

Text #9

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.3951. Min Act: -0.0000

Data Index: 954799 (The Pile)

Max Activating Token Index: 838

Text #10

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.4627. Min Act: -0.0000

Data Index: 1427298 (The Pile)

Max Activating Token Index: 14

Text #11

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.2852. Min Act: -0.0000

Data Index: 837329 (The Pile)

Max Activating Token Index: 767

Text #12

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.4877. Min Act: -0.0000

Data Index: 1341781 (The Pile)

Max Activating Token Index: 24

Text #13

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.4739. Min Act: -0.0000

Data Index: 1254544 (The Pile)

Max Activating Token Index: 593

Text #14

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.4044. Min Act: -0.0000

Data Index: 958296 (The Pile)

Max Activating Token Index: 961

Text #15

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.3620. Min Act: -0.0000

Data Index: 983601 (The Pile)

Max Activating Token Index: 486

Text #16

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.4057. Min Act: -0.0000

Data Index: 1164567 (The Pile)

Max Activating Token Index: 808

Text #17

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.1452. Min Act: -0.0000

Data Index: 996006 (The Pile)

Max Activating Token Index: 48

Text #18

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.2049. Min Act: -0.0000

Data Index: 989975 (The Pile)

Max Activating Token Index: 35

Text #19

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.2900. Min Act: -0.0000

Data Index: 734846 (The Pile)

Max Activating Token Index: 758