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

Dataset: The Pile

Neuron 405 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: 1.7806. Min Range: -1.7806

Max Act: 1.7806. Min Act: -0.0000

Data Index: 1632838 (The Pile)

Max Activating Token Index: 21

Text #1

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.7412. Min Act: -0.0000

Data Index: 1885090 (The Pile)

Max Activating Token Index: 943

Text #2

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.7704. Min Act: -0.0000

Data Index: 1053044 (The Pile)

Max Activating Token Index: 633

Text #3

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.6226. Min Act: 0.0000

Data Index: 558588 (The Pile)

Max Activating Token Index: 449

Text #4

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.5300. Min Act: 0.0001

Data Index: 1536727 (The Pile)

Max Activating Token Index: 370

Text #5

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.4505. Min Act: -0.0000

Data Index: 1045579 (The Pile)

Max Activating Token Index: 131

Text #6

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.5975. Min Act: -0.0000

Data Index: 1262281 (The Pile)

Max Activating Token Index: 153

Text #7

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.5849. Min Act: -0.0000

Data Index: 1542957 (The Pile)

Max Activating Token Index: 984

Text #8

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.4735. Min Act: -0.0000

Data Index: 190865 (The Pile)

Max Activating Token Index: 266

Text #9

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.3895. Min Act: -0.0000

Data Index: 1697813 (The Pile)

Max Activating Token Index: 256

Text #10

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.4242. Min Act: 0.0000

Data Index: 360510 (The Pile)

Max Activating Token Index: 405

Text #11

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.4155. Min Act: -0.0000

Data Index: 869389 (The Pile)

Max Activating Token Index: 433

Text #12

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.4529. Min Act: -0.0000

Data Index: 1519651 (The Pile)

Max Activating Token Index: 774

Text #13

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.3635. Min Act: -0.0000

Data Index: 446424 (The Pile)

Max Activating Token Index: 350

Text #14

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.2670. Min Act: -0.0000

Data Index: 1342800 (The Pile)

Max Activating Token Index: 131

Text #15

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.4005. Min Act: -0.0000

Data Index: 1725767 (The Pile)

Max Activating Token Index: 18

Text #16

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.2463. Min Act: -0.0000

Data Index: 718341 (The Pile)

Max Activating Token Index: 493

Text #17

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.3805. Min Act: -0.0000

Data Index: 156819 (The Pile)

Max Activating Token Index: 758

Text #18

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.2229. Min Act: -0.0000

Data Index: 349383 (The Pile)

Max Activating Token Index: 998

Text #19

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.2081. Min Act: -0.0000

Data Index: 752028 (The Pile)

Max Activating Token Index: 68