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

Dataset: The Pile

Neuron 1915 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.9643. Min Act: -0.0000

Data Index: 544513 (The Pile)

Max Activating Token Index: 139

Text #1

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.7955. Min Act: -0.0000

Data Index: 1438657 (The Pile)

Max Activating Token Index: 485

Text #2

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.9841. Min Act: -0.0000

Data Index: 606453 (The Pile)

Max Activating Token Index: 406

Text #3

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.8020. Min Act: -0.0000

Data Index: 1687143 (The Pile)

Max Activating Token Index: 236

Text #4

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.8925. Min Act: -0.0000

Data Index: 683933 (The Pile)

Max Activating Token Index: 219

Text #5

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.8786. Min Act: -0.0000

Data Index: 1219948 (The Pile)

Max Activating Token Index: 198

Text #6

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.5684. Min Act: -0.0000

Data Index: 1448541 (The Pile)

Max Activating Token Index: 535

Text #7

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.7480. Min Act: -0.0000

Data Index: 1625911 (The Pile)

Max Activating Token Index: 171

Text #8

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.8617. Min Act: -0.0000

Data Index: 603281 (The Pile)

Max Activating Token Index: 917

Text #9

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.7296. Min Act: -0.0000

Data Index: 335829 (The Pile)

Max Activating Token Index: 1017

Text #10

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.7622. Min Act: -0.0000

Data Index: 1291772 (The Pile)

Max Activating Token Index: 746

Text #11

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.6976. Min Act: -0.0000

Data Index: 1284727 (The Pile)

Max Activating Token Index: 280

Text #12

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.6988. Min Act: -0.0000

Data Index: 981776 (The Pile)

Max Activating Token Index: 648

Text #13

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.6941. Min Act: -0.0000

Data Index: 1513669 (The Pile)

Max Activating Token Index: 438

Text #14

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.5417. Min Act: -0.0000

Data Index: 73923 (The Pile)

Max Activating Token Index: 836

Text #15

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.6789. Min Act: -0.0000

Data Index: 855708 (The Pile)

Max Activating Token Index: 20

Text #16

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.5527. Min Act: -0.0000

Data Index: 1124551 (The Pile)

Max Activating Token Index: 885

Text #17

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.7707. Min Act: -0.0000

Data Index: 1293339 (The Pile)

Max Activating Token Index: 668

Text #18

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.8253. Min Act: -0.0000

Data Index: 242748 (The Pile)

Max Activating Token Index: 457

Text #19

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.6154. Min Act: -0.0000

Data Index: 1008655 (The Pile)

Max Activating Token Index: 133