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

Dataset: The Pile

Neuron 3747 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.4939. Min Act: -0.0000

Data Index: 562385 (The Pile)

Max Activating Token Index: 997

Text #1

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.5076. Min Act: -0.0000

Data Index: 472238 (The Pile)

Max Activating Token Index: 881

Text #2

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.5063. Min Act: -0.0000

Data Index: 1068762 (The Pile)

Max Activating Token Index: 465

Text #3

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.5014. Min Act: -0.0000

Data Index: 73053 (The Pile)

Max Activating Token Index: 318

Text #4

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.4801. Min Act: -0.0000

Data Index: 711719 (The Pile)

Max Activating Token Index: 331

Text #5

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.4688. Min Act: -0.0000

Data Index: 1182833 (The Pile)

Max Activating Token Index: 954

Text #6

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.4710. Min Act: -0.0000

Data Index: 1858098 (The Pile)

Max Activating Token Index: 471

Text #7

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.4773. Min Act: -0.0000

Data Index: 412347 (The Pile)

Max Activating Token Index: 682

Text #8

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.4340. Min Act: -0.0000

Data Index: 1410906 (The Pile)

Max Activating Token Index: 859

Text #9

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.4410. Min Act: -0.0000

Data Index: 1409937 (The Pile)

Max Activating Token Index: 600

Text #10

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.4382. Min Act: -0.0000

Data Index: 1799156 (The Pile)

Max Activating Token Index: 121

Text #11

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.4382. Min Act: -0.0000

Data Index: 619968 (The Pile)

Max Activating Token Index: 12

Text #12

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.4514. Min Act: -0.0000

Data Index: 274317 (The Pile)

Max Activating Token Index: 564

Text #13

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.4489. Min Act: -0.0000

Data Index: 1399065 (The Pile)

Max Activating Token Index: 696

Text #14

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.4141. Min Act: -0.0000

Data Index: 1110105 (The Pile)

Max Activating Token Index: 400

Text #15

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.4102. Min Act: -0.0000

Data Index: 1337167 (The Pile)

Max Activating Token Index: 681

Text #16

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.4269. Min Act: -0.0000

Data Index: 1743584 (The Pile)

Max Activating Token Index: 824

Text #17

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.4216. Min Act: -0.0000

Data Index: 1739765 (The Pile)

Max Activating Token Index: 880

Text #18

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.4455. Min Act: -0.0000

Data Index: 542299 (The Pile)

Max Activating Token Index: 690

Text #19

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.4152. Min Act: -0.0000

Data Index: 299881 (The Pile)

Max Activating Token Index: 184