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

Dataset: The Pile

Neuron 797 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: 0.8384. Min Range: -0.8384

Max Act: 0.8384. Min Act: -0.0000

Data Index: 1836909 (The Pile)

Max Activating Token Index: 195

Text #1

Max Range: 0.8384. Min Range: -0.8384

Max Act: 0.8027. Min Act: -0.0000

Data Index: 1195141 (The Pile)

Max Activating Token Index: 41

Text #2

Max Range: 0.8384. Min Range: -0.8384

Max Act: 0.7577. Min Act: -0.0000

Data Index: 771818 (The Pile)

Max Activating Token Index: 945

Text #3

Max Range: 0.8384. Min Range: -0.8384

Max Act: 0.7723. Min Act: -0.0000

Data Index: 1874558 (The Pile)

Max Activating Token Index: 45

Text #4

Max Range: 0.8384. Min Range: -0.8384

Max Act: 0.7593. Min Act: -0.0000

Data Index: 1825021 (The Pile)

Max Activating Token Index: 140

Text #5

Max Range: 0.8384. Min Range: -0.8384

Max Act: 0.7215. Min Act: -0.0000

Data Index: 392955 (The Pile)

Max Activating Token Index: 208

Text #6

Max Range: 0.8384. Min Range: -0.8384

Max Act: 0.6926. Min Act: -0.0000

Data Index: 660578 (The Pile)

Max Activating Token Index: 1007

Text #7

Max Range: 0.8384. Min Range: -0.8384

Max Act: 0.6890. Min Act: -0.0000

Data Index: 1879855 (The Pile)

Max Activating Token Index: 448

Text #8

Max Range: 0.8384. Min Range: -0.8384

Max Act: 0.6672. Min Act: -0.0000

Data Index: 868210 (The Pile)

Max Activating Token Index: 959

Text #9

Max Range: 0.8384. Min Range: -0.8384

Max Act: 0.6730. Min Act: -0.0000

Data Index: 1729385 (The Pile)

Max Activating Token Index: 861

Text #10

Max Range: 0.8384. Min Range: -0.8384

Max Act: 0.6905. Min Act: -0.0000

Data Index: 1472241 (The Pile)

Max Activating Token Index: 408

Text #11

Max Range: 0.8384. Min Range: -0.8384

Max Act: 0.6895. Min Act: -0.0000

Data Index: 275838 (The Pile)

Max Activating Token Index: 63

Text #12

Max Range: 0.8384. Min Range: -0.8384

Max Act: 0.5995. Min Act: -0.0000

Data Index: 336728 (The Pile)

Max Activating Token Index: 529

Text #13

Max Range: 0.8384. Min Range: -0.8384

Max Act: 0.6126. Min Act: -0.0000

Data Index: 1950621 (The Pile)

Max Activating Token Index: 821

Text #14

Max Range: 0.8384. Min Range: -0.8384

Max Act: 0.6102. Min Act: -0.0000

Data Index: 657879 (The Pile)

Max Activating Token Index: 896

Text #15

Max Range: 0.8384. Min Range: -0.8384

Max Act: 0.6303. Min Act: -0.0000

Data Index: 1119198 (The Pile)

Max Activating Token Index: 219

Text #16

Max Range: 0.8384. Min Range: -0.8384

Max Act: 0.6271. Min Act: -0.0000

Data Index: 1053117 (The Pile)

Max Activating Token Index: 405

Text #17

Max Range: 0.8384. Min Range: -0.8384

Max Act: 0.5811. Min Act: -0.0000

Data Index: 1784766 (The Pile)

Max Activating Token Index: 100

Text #18

Max Range: 0.8384. Min Range: -0.8384

Max Act: 0.6015. Min Act: -0.0000

Data Index: 1063609 (The Pile)

Max Activating Token Index: 510

Text #19

Max Range: 0.8384. Min Range: -0.8384

Max Act: 0.5406. Min Act: -0.0000

Data Index: 1467728 (The Pile)

Max Activating Token Index: 788