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

Dataset: The Pile

Neuron 1903 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: 0.9014. Min Range: -0.9014

Max Act: 0.9014. Min Act: -0.0000

Data Index: 712637 (The Pile)

Max Activating Token Index: 263

Text #1

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.8944. Min Act: -0.0000

Data Index: 1111066 (The Pile)

Max Activating Token Index: 305

Text #2

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.8753. Min Act: -0.0000

Data Index: 779178 (The Pile)

Max Activating Token Index: 427

Text #3

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.8296. Min Act: -0.0000

Data Index: 222172 (The Pile)

Max Activating Token Index: 954

Text #4

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.8350. Min Act: -0.0000

Data Index: 578992 (The Pile)

Max Activating Token Index: 189

Text #5

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.8839. Min Act: -0.0000

Data Index: 996560 (The Pile)

Max Activating Token Index: 825

Text #6

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.7820. Min Act: -0.0000

Data Index: 1472293 (The Pile)

Max Activating Token Index: 463

Text #7

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.7810. Min Act: -0.0000

Data Index: 1313058 (The Pile)

Max Activating Token Index: 492

Text #8

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.7340. Min Act: -0.0000

Data Index: 750749 (The Pile)

Max Activating Token Index: 515

Text #9

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.7556. Min Act: -0.0000

Data Index: 170018 (The Pile)

Max Activating Token Index: 721

Text #10

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.7242. Min Act: -0.0000

Data Index: 1836554 (The Pile)

Max Activating Token Index: 136

Text #11

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.7841. Min Act: -0.0000

Data Index: 1461601 (The Pile)

Max Activating Token Index: 262

Text #12

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.7136. Min Act: -0.0000

Data Index: 1504946 (The Pile)

Max Activating Token Index: 554

Text #13

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.7373. Min Act: -0.0000

Data Index: 1669652 (The Pile)

Max Activating Token Index: 260

Text #14

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.6983. Min Act: -0.0000

Data Index: 904681 (The Pile)

Max Activating Token Index: 876

Text #15

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.7307. Min Act: -0.0000

Data Index: 706591 (The Pile)

Max Activating Token Index: 872

Text #16

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.7129. Min Act: -0.0000

Data Index: 1242884 (The Pile)

Max Activating Token Index: 862

Text #17

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.7283. Min Act: -0.0000

Data Index: 1593806 (The Pile)

Max Activating Token Index: 569

Text #18

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.7435. Min Act: -0.0000

Data Index: 1243723 (The Pile)

Max Activating Token Index: 554

Text #19

Max Range: 0.9014. Min Range: -0.9014

Max Act: 0.6831. Min Act: -0.0000

Data Index: 300784 (The Pile)

Max Activating Token Index: 660