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

Dataset: The Pile

Neuron 4423 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: 0.7615. Min Range: -0.7615

Max Act: 0.7615. Min Act: -0.0000

Data Index: 109037 (The Pile)

Max Activating Token Index: 200

Text #1

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5731. Min Act: -0.0000

Data Index: 750221 (The Pile)

Max Activating Token Index: 289

Text #2

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5715. Min Act: -0.0000

Data Index: 209770 (The Pile)

Max Activating Token Index: 173

Text #3

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5327. Min Act: -0.0000

Data Index: 1758817 (The Pile)

Max Activating Token Index: 141

Text #4

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5397. Min Act: -0.0000

Data Index: 1619040 (The Pile)

Max Activating Token Index: 394

Text #5

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5294. Min Act: -0.0000

Data Index: 1184356 (The Pile)

Max Activating Token Index: 346

Text #6

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5278. Min Act: -0.0000

Data Index: 821106 (The Pile)

Max Activating Token Index: 22

Text #7

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5066. Min Act: -0.0000

Data Index: 279432 (The Pile)

Max Activating Token Index: 915

Text #8

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5037. Min Act: -0.0000

Data Index: 322891 (The Pile)

Max Activating Token Index: 102

Text #9

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5002. Min Act: -0.0000

Data Index: 1709759 (The Pile)

Max Activating Token Index: 9

Text #10

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.4965. Min Act: -0.0000

Data Index: 775612 (The Pile)

Max Activating Token Index: 285

Text #11

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.4747. Min Act: -0.0000

Data Index: 1142015 (The Pile)

Max Activating Token Index: 181

Text #12

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.4760. Min Act: -0.0000

Data Index: 1103422 (The Pile)

Max Activating Token Index: 527

Text #13

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.4410. Min Act: -0.0000

Data Index: 996753 (The Pile)

Max Activating Token Index: 716

Text #14

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.4836. Min Act: -0.0000

Data Index: 431183 (The Pile)

Max Activating Token Index: 529

Text #15

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.4386. Min Act: -0.0000

Data Index: 1343854 (The Pile)

Max Activating Token Index: 950

Text #16

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.4792. Min Act: 0.0000

Data Index: 1075504 (The Pile)

Max Activating Token Index: 750

Text #17

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.4853. Min Act: -0.0000

Data Index: 110908 (The Pile)

Max Activating Token Index: 799

Text #18

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.4769. Min Act: -0.0000

Data Index: 639910 (The Pile)

Max Activating Token Index: 600

Text #19

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.4471. Min Act: -0.0000

Data Index: 1899428 (The Pile)

Max Activating Token Index: 25