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

Dataset: The Pile

Neuron 4634 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: 1.0365. Min Range: -1.0365

Max Act: 1.0365. Min Act: -0.0000

Data Index: 1521251 (The Pile)

Max Activating Token Index: 705

Text #1

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.9231. Min Act: -0.0000

Data Index: 1430865 (The Pile)

Max Activating Token Index: 867

Text #2

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.9839. Min Act: -0.0000

Data Index: 521412 (The Pile)

Max Activating Token Index: 491

Text #3

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.9100. Min Act: -0.0000

Data Index: 1032202 (The Pile)

Max Activating Token Index: 65

Text #4

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.9287. Min Act: -0.0000

Data Index: 567327 (The Pile)

Max Activating Token Index: 595

Text #5

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.8886. Min Act: -0.0000

Data Index: 1095723 (The Pile)

Max Activating Token Index: 702

Text #6

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.7763. Min Act: -0.0000

Data Index: 518726 (The Pile)

Max Activating Token Index: 196

Text #7

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.6446. Min Act: -0.0000

Data Index: 663908 (The Pile)

Max Activating Token Index: 192

Text #8

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.7026. Min Act: -0.0000

Data Index: 1890600 (The Pile)

Max Activating Token Index: 971

Text #9

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.6868. Min Act: -0.0000

Data Index: 1355412 (The Pile)

Max Activating Token Index: 886

Text #10

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.5950. Min Act: -0.0000

Data Index: 291884 (The Pile)

Max Activating Token Index: 796

Text #11

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.6040. Min Act: -0.0000

Data Index: 1706966 (The Pile)

Max Activating Token Index: 330

Text #12

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.6062. Min Act: -0.0000

Data Index: 1133672 (The Pile)

Max Activating Token Index: 843

Text #13

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.6410. Min Act: -0.0000

Data Index: 242920 (The Pile)

Max Activating Token Index: 431

Text #14

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.6495. Min Act: -0.0000

Data Index: 70768 (The Pile)

Max Activating Token Index: 806

Text #15

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.6319. Min Act: -0.0000

Data Index: 156912 (The Pile)

Max Activating Token Index: 191

Text #16

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.5886. Min Act: -0.0000

Data Index: 832775 (The Pile)

Max Activating Token Index: 31

Text #17

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.6769. Min Act: -0.0000

Data Index: 1949785 (The Pile)

Max Activating Token Index: 924

Text #18

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.5167. Min Act: -0.0000

Data Index: 580021 (The Pile)

Max Activating Token Index: 75

Text #19

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.5422. Min Act: -0.0000

Data Index: 1248945 (The Pile)

Max Activating Token Index: 473