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

Dataset: The Pile

Neuron 1895 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.6997. Min Act: -0.0000

Data Index: 1012520 (The Pile)

Max Activating Token Index: 606

Text #1

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.5159. Min Act: -0.0000

Data Index: 1699815 (The Pile)

Max Activating Token Index: 774

Text #2

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.4887. Min Act: -0.0000

Data Index: 631708 (The Pile)

Max Activating Token Index: 323

Text #3

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.4764. Min Act: -0.0000

Data Index: 1287875 (The Pile)

Max Activating Token Index: 390

Text #4

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.4525. Min Act: -0.0000

Data Index: 371215 (The Pile)

Max Activating Token Index: 514

Text #5

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.4804. Min Act: -0.0000

Data Index: 639421 (The Pile)

Max Activating Token Index: 447

Text #6

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.4607. Min Act: -0.0000

Data Index: 891610 (The Pile)

Max Activating Token Index: 755

Text #7

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.4734. Min Act: -0.0000

Data Index: 1670267 (The Pile)

Max Activating Token Index: 413

Text #8

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.4494. Min Act: -0.0000

Data Index: 121115 (The Pile)

Max Activating Token Index: 548

Text #9

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.4072. Min Act: -0.0000

Data Index: 1433004 (The Pile)

Max Activating Token Index: 576

Text #10

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.4454. Min Act: -0.0000

Data Index: 1342594 (The Pile)

Max Activating Token Index: 402

Text #11

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.4684. Min Act: -0.0000

Data Index: 1785064 (The Pile)

Max Activating Token Index: 1009

Text #12

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.4447. Min Act: -0.0000

Data Index: 784784 (The Pile)

Max Activating Token Index: 710

Text #13

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.4392. Min Act: -0.0000

Data Index: 268653 (The Pile)

Max Activating Token Index: 950

Text #14

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.4059. Min Act: -0.0000

Data Index: 512411 (The Pile)

Max Activating Token Index: 786

Text #15

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.4167. Min Act: -0.0000

Data Index: 1068422 (The Pile)

Max Activating Token Index: 202

Text #16

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.4120. Min Act: -0.0000

Data Index: 1442765 (The Pile)

Max Activating Token Index: 194

Text #17

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.4243. Min Act: -0.0000

Data Index: 1878276 (The Pile)

Max Activating Token Index: 506

Text #18

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.3964. Min Act: -0.0000

Data Index: 840690 (The Pile)

Max Activating Token Index: 271

Text #19

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.4163. Min Act: -0.0000

Data Index: 1715571 (The Pile)

Max Activating Token Index: 780