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

Dataset: The Pile

Neuron 3359 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: 0.8935. Min Range: -0.8935

Max Act: 0.8935. Min Act: -0.0000

Data Index: 972267 (The Pile)

Max Activating Token Index: 833

Text #1

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.8325. Min Act: -0.0000

Data Index: 468586 (The Pile)

Max Activating Token Index: 799

Text #2

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.8398. Min Act: -0.0000

Data Index: 1542194 (The Pile)

Max Activating Token Index: 470

Text #3

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.6794. Min Act: -0.0000

Data Index: 606875 (The Pile)

Max Activating Token Index: 673

Text #4

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.7575. Min Act: -0.0000

Data Index: 868670 (The Pile)

Max Activating Token Index: 136

Text #5

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.7453. Min Act: -0.0000

Data Index: 926723 (The Pile)

Max Activating Token Index: 669

Text #6

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.7751. Min Act: -0.0000

Data Index: 183695 (The Pile)

Max Activating Token Index: 682

Text #7

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.7689. Min Act: -0.0000

Data Index: 680890 (The Pile)

Max Activating Token Index: 143

Text #8

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.7681. Min Act: -0.0000

Data Index: 1846423 (The Pile)

Max Activating Token Index: 438

Text #9

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.6965. Min Act: -0.0000

Data Index: 848461 (The Pile)

Max Activating Token Index: 61

Text #10

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.6009. Min Act: -0.0000

Data Index: 1126957 (The Pile)

Max Activating Token Index: 458

Text #11

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.6516. Min Act: -0.0000

Data Index: 500856 (The Pile)

Max Activating Token Index: 724

Text #12

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.7409. Min Act: -0.0000

Data Index: 795962 (The Pile)

Max Activating Token Index: 111

Text #13

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.6567. Min Act: -0.0000

Data Index: 1837153 (The Pile)

Max Activating Token Index: 925

Text #14

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.6478. Min Act: -0.0000

Data Index: 1494615 (The Pile)

Max Activating Token Index: 52

Text #15

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.5781. Min Act: -0.0000

Data Index: 1389284 (The Pile)

Max Activating Token Index: 257

Text #16

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.6459. Min Act: -0.0000

Data Index: 1541930 (The Pile)

Max Activating Token Index: 23

Text #17

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.6914. Min Act: -0.0000

Data Index: 683771 (The Pile)

Max Activating Token Index: 210

Text #18

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.5885. Min Act: -0.0000

Data Index: 1261980 (The Pile)

Max Activating Token Index: 317

Text #19

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.6251. Min Act: -0.0000

Data Index: 1767453 (The Pile)

Max Activating Token Index: 138