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

Dataset: The Pile

Neuron 4065 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: 0.5940. Min Range: -0.5940

Max Act: 0.5645. Min Act: -0.0000

Data Index: 837824 (The Pile)

Max Activating Token Index: 742

Text #1

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.5940. Min Act: -0.0000

Data Index: 903732 (The Pile)

Max Activating Token Index: 496

Text #2

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.5383. Min Act: -0.0000

Data Index: 894486 (The Pile)

Max Activating Token Index: 461

Text #3

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.5536. Min Act: -0.0000

Data Index: 113035 (The Pile)

Max Activating Token Index: 311

Text #4

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.5473. Min Act: -0.0000

Data Index: 861654 (The Pile)

Max Activating Token Index: 127

Text #5

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.5226. Min Act: -0.0000

Data Index: 1342933 (The Pile)

Max Activating Token Index: 428

Text #6

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.4991. Min Act: -0.0000

Data Index: 1967345 (The Pile)

Max Activating Token Index: 92

Text #7

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.4822. Min Act: -0.0000

Data Index: 828595 (The Pile)

Max Activating Token Index: 371

Text #8

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.4622. Min Act: -0.0000

Data Index: 374420 (The Pile)

Max Activating Token Index: 97

Text #9

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.4568. Min Act: -0.0000

Data Index: 383681 (The Pile)

Max Activating Token Index: 188

Text #10

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.3947. Min Act: -0.0000

Data Index: 703834 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.4539. Min Act: -0.0000

Data Index: 1523539 (The Pile)

Max Activating Token Index: 635

Text #12

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.4799. Min Act: -0.0000

Data Index: 826943 (The Pile)

Max Activating Token Index: 1005

Text #13

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.4247. Min Act: -0.0000

Data Index: 517172 (The Pile)

Max Activating Token Index: 71

Text #14

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.4163. Min Act: -0.0000

Data Index: 983635 (The Pile)

Max Activating Token Index: 71

Text #15

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.4476. Min Act: -0.0000

Data Index: 59913 (The Pile)

Max Activating Token Index: 188

Text #16

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.3915. Min Act: -0.0000

Data Index: 1612867 (The Pile)

Max Activating Token Index: 747

Text #17

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.4132. Min Act: -0.0000

Data Index: 91384 (The Pile)

Max Activating Token Index: 780

Text #18

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.4098. Min Act: -0.0000

Data Index: 671959 (The Pile)

Max Activating Token Index: 623

Text #19

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.4405. Min Act: -0.0000

Data Index: 433118 (The Pile)

Max Activating Token Index: 466