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

Dataset: The Pile

Neuron 1095 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8727. Min Range: -1.8727

Max Act: 1.8727. Min Act: -0.0000

Data Index: 199592 (The Pile)

Max Activating Token Index: 94

Text #1

Max Range: 1.8727. Min Range: -1.8727

Max Act: 1.5486. Min Act: -0.0000

Data Index: 905519 (The Pile)

Max Activating Token Index: 12

Text #2

Max Range: 1.8727. Min Range: -1.8727

Max Act: 1.2493. Min Act: -0.0000

Data Index: 512134 (The Pile)

Max Activating Token Index: 867

Text #3

Max Range: 1.8727. Min Range: -1.8727

Max Act: 0.8890. Min Act: -0.0000

Data Index: 1981586 (The Pile)

Max Activating Token Index: 240

Text #4

Max Range: 1.8727. Min Range: -1.8727

Max Act: 0.8427. Min Act: -0.0000

Data Index: 782482 (The Pile)

Max Activating Token Index: 569

Text #5

Max Range: 1.8727. Min Range: -1.8727

Max Act: 0.8044. Min Act: -0.0000

Data Index: 1781159 (The Pile)

Max Activating Token Index: 410

Text #6

Max Range: 1.8727. Min Range: -1.8727

Max Act: 0.6981. Min Act: -0.0000

Data Index: 713759 (The Pile)

Max Activating Token Index: 28

Text #7

Max Range: 1.8727. Min Range: -1.8727

Max Act: 0.7148. Min Act: -0.0000

Data Index: 755328 (The Pile)

Max Activating Token Index: 630

Text #8

Max Range: 1.8727. Min Range: -1.8727

Max Act: 0.7531. Min Act: -0.0000

Data Index: 362179 (The Pile)

Max Activating Token Index: 597

Text #9

Max Range: 1.8727. Min Range: -1.8727

Max Act: 0.6967. Min Act: -0.0000

Data Index: 530511 (The Pile)

Max Activating Token Index: 606

Text #10

Max Range: 1.8727. Min Range: -1.8727

Max Act: 0.6892. Min Act: -0.0000

Data Index: 1737840 (The Pile)

Max Activating Token Index: 579

Text #11

Max Range: 1.8727. Min Range: -1.8727

Max Act: 0.5043. Min Act: -0.0000

Data Index: 1184364 (The Pile)

Max Activating Token Index: 776

Text #12

Max Range: 1.8727. Min Range: -1.8727

Max Act: 0.7075. Min Act: -0.0000

Data Index: 1370374 (The Pile)

Max Activating Token Index: 798

Text #13

Max Range: 1.8727. Min Range: -1.8727

Max Act: 0.6676. Min Act: -0.0000

Data Index: 1910323 (The Pile)

Max Activating Token Index: 833

Text #14

Max Range: 1.8727. Min Range: -1.8727

Max Act: 0.5698. Min Act: -0.0000

Data Index: 1374068 (The Pile)

Max Activating Token Index: 147

Text #15

Max Range: 1.8727. Min Range: -1.8727

Max Act: 0.4778. Min Act: -0.0000

Data Index: 651435 (The Pile)

Max Activating Token Index: 456

Text #16

Max Range: 1.8727. Min Range: -1.8727

Max Act: 0.4819. Min Act: -0.0000

Data Index: 795913 (The Pile)

Max Activating Token Index: 738

Text #17

Max Range: 1.8727. Min Range: -1.8727

Max Act: 0.4597. Min Act: -0.0000

Data Index: 675644 (The Pile)

Max Activating Token Index: 223

Text #18

Max Range: 1.8727. Min Range: -1.8727

Max Act: 0.5739. Min Act: -0.0000

Data Index: 338996 (The Pile)

Max Activating Token Index: 259

Text #19

Max Range: 1.8727. Min Range: -1.8727

Max Act: 0.5010. Min Act: -0.0000

Data Index: 621681 (The Pile)

Max Activating Token Index: 811