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

Dataset: The Pile

Neuron 4444 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: 1.1531. Min Range: -1.1531

Max Act: 1.1531. Min Act: -0.0000

Data Index: 871145 (The Pile)

Max Activating Token Index: 459

Text #1

Max Range: 1.1531. Min Range: -1.1531

Max Act: 1.0718. Min Act: -0.0000

Data Index: 654603 (The Pile)

Max Activating Token Index: 133

Text #2

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.9421. Min Act: -0.0000

Data Index: 843824 (The Pile)

Max Activating Token Index: 250

Text #3

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.9166. Min Act: -0.0000

Data Index: 1035783 (The Pile)

Max Activating Token Index: 902

Text #4

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.9257. Min Act: -0.0000

Data Index: 1804454 (The Pile)

Max Activating Token Index: 421

Text #5

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.9110. Min Act: -0.0000

Data Index: 971881 (The Pile)

Max Activating Token Index: 483

Text #6

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.8190. Min Act: -0.0000

Data Index: 1501167 (The Pile)

Max Activating Token Index: 419

Text #7

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.8948. Min Act: -0.0000

Data Index: 1848087 (The Pile)

Max Activating Token Index: 509

Text #8

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.8756. Min Act: -0.0000

Data Index: 723373 (The Pile)

Max Activating Token Index: 802

Text #9

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.8078. Min Act: -0.0000

Data Index: 1857791 (The Pile)

Max Activating Token Index: 48

Text #10

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.8712. Min Act: -0.0000

Data Index: 344432 (The Pile)

Max Activating Token Index: 174

Text #11

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.8636. Min Act: -0.0000

Data Index: 1135100 (The Pile)

Max Activating Token Index: 600

Text #12

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.8278. Min Act: -0.0000

Data Index: 1606100 (The Pile)

Max Activating Token Index: 534

Text #13

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.7823. Min Act: -0.0000

Data Index: 941169 (The Pile)

Max Activating Token Index: 715

Text #14

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.8306. Min Act: -0.0000

Data Index: 1053450 (The Pile)

Max Activating Token Index: 736

Text #15

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.8445. Min Act: -0.0000

Data Index: 228345 (The Pile)

Max Activating Token Index: 166

Text #16

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.7484. Min Act: -0.0000

Data Index: 208834 (The Pile)

Max Activating Token Index: 540

Text #17

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.8327. Min Act: -0.0000

Data Index: 1328881 (The Pile)

Max Activating Token Index: 140

Text #18

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.7276. Min Act: -0.0000

Data Index: 1349391 (The Pile)

Max Activating Token Index: 946

Text #19

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.7820. Min Act: -0.0000

Data Index: 608650 (The Pile)

Max Activating Token Index: 471