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

Dataset: The Pile

Neuron 1626 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7651. Min Range: -3.7651

Max Act: 3.0070. Min Act: -0.0000

Data Index: 1594018 (The Pile)

Max Activating Token Index: 851

Text #1

Max Range: 3.7651. Min Range: -3.7651

Max Act: 3.7651. Min Act: -0.0000

Data Index: 1139161 (The Pile)

Max Activating Token Index: 165

Text #2

Max Range: 3.7651. Min Range: -3.7651

Max Act: 2.9824. Min Act: -0.0000

Data Index: 776883 (The Pile)

Max Activating Token Index: 870

Text #3

Max Range: 3.7651. Min Range: -3.7651

Max Act: 3.1324. Min Act: -0.0000

Data Index: 1422855 (The Pile)

Max Activating Token Index: 531

Text #4

Max Range: 3.7651. Min Range: -3.7651

Max Act: 2.8956. Min Act: -0.0000

Data Index: 1729449 (The Pile)

Max Activating Token Index: 113

Text #5

Max Range: 3.7651. Min Range: -3.7651

Max Act: 2.7828. Min Act: -0.0000

Data Index: 1217178 (The Pile)

Max Activating Token Index: 609

Text #6

Max Range: 3.7651. Min Range: -3.7651

Max Act: 2.9187. Min Act: -0.0000

Data Index: 1588289 (The Pile)

Max Activating Token Index: 450

Text #7

Max Range: 3.7651. Min Range: -3.7651

Max Act: 3.0104. Min Act: -0.0001

Data Index: 75007 (The Pile)

Max Activating Token Index: 860

Text #8

Max Range: 3.7651. Min Range: -3.7651

Max Act: 3.0977. Min Act: -0.0000

Data Index: 845061 (The Pile)

Max Activating Token Index: 799

Text #9

Max Range: 3.7651. Min Range: -3.7651

Max Act: 3.0997. Min Act: -0.0000

Data Index: 1007612 (The Pile)

Max Activating Token Index: 506

Text #10

Max Range: 3.7651. Min Range: -3.7651

Max Act: 2.9970. Min Act: -0.0000

Data Index: 1261310 (The Pile)

Max Activating Token Index: 720

Text #11

Max Range: 3.7651. Min Range: -3.7651

Max Act: 2.8390. Min Act: -0.0000

Data Index: 315302 (The Pile)

Max Activating Token Index: 851

Text #12

Max Range: 3.7651. Min Range: -3.7651

Max Act: 2.8005. Min Act: -0.0000

Data Index: 832813 (The Pile)

Max Activating Token Index: 372

Text #13

Max Range: 3.7651. Min Range: -3.7651

Max Act: 2.7367. Min Act: -0.0000

Data Index: 220904 (The Pile)

Max Activating Token Index: 209

Text #14

Max Range: 3.7651. Min Range: -3.7651

Max Act: 2.6290. Min Act: -0.0000

Data Index: 1315131 (The Pile)

Max Activating Token Index: 823

Text #15

Max Range: 3.7651. Min Range: -3.7651

Max Act: 2.6139. Min Act: -0.0000

Data Index: 1789562 (The Pile)

Max Activating Token Index: 685

Text #16

Max Range: 3.7651. Min Range: -3.7651

Max Act: 2.6564. Min Act: -0.0000

Data Index: 55421 (The Pile)

Max Activating Token Index: 808

Text #17

Max Range: 3.7651. Min Range: -3.7651

Max Act: 2.5592. Min Act: -0.0000

Data Index: 634752 (The Pile)

Max Activating Token Index: 362

Text #18

Max Range: 3.7651. Min Range: -3.7651

Max Act: 2.7689. Min Act: -0.0000

Data Index: 1139173 (The Pile)

Max Activating Token Index: 874

Text #19

Max Range: 3.7651. Min Range: -3.7651

Max Act: 2.9000. Min Act: -0.0001

Data Index: 350932 (The Pile)

Max Activating Token Index: 797