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

Dataset: The Pile

Neuron 24 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: 1.6940. Min Range: -1.6940

Max Act: 1.6940. Min Act: -0.0000

Data Index: 1370231 (The Pile)

Max Activating Token Index: 567

Text #1

Max Range: 1.6940. Min Range: -1.6940

Max Act: 1.3245. Min Act: -0.0000

Data Index: 1085563 (The Pile)

Max Activating Token Index: 660

Text #2

Max Range: 1.6940. Min Range: -1.6940

Max Act: 1.2967. Min Act: -0.0000

Data Index: 361601 (The Pile)

Max Activating Token Index: 762

Text #3

Max Range: 1.6940. Min Range: -1.6940

Max Act: 1.2500. Min Act: -0.0000

Data Index: 1176649 (The Pile)

Max Activating Token Index: 823

Text #4

Max Range: 1.6940. Min Range: -1.6940

Max Act: 1.2562. Min Act: -0.0000

Data Index: 1013681 (The Pile)

Max Activating Token Index: 42

Text #5

Max Range: 1.6940. Min Range: -1.6940

Max Act: 1.3603. Min Act: -0.0000

Data Index: 311384 (The Pile)

Max Activating Token Index: 417

Text #6

Max Range: 1.6940. Min Range: -1.6940

Max Act: 1.1781. Min Act: -0.0000

Data Index: 1076336 (The Pile)

Max Activating Token Index: 497

Text #7

Max Range: 1.6940. Min Range: -1.6940

Max Act: 1.0793. Min Act: -0.0000

Data Index: 1267714 (The Pile)

Max Activating Token Index: 255

Text #8

Max Range: 1.6940. Min Range: -1.6940

Max Act: 0.9321. Min Act: -0.0000

Data Index: 1837016 (The Pile)

Max Activating Token Index: 330

Text #9

Max Range: 1.6940. Min Range: -1.6940

Max Act: 0.9035. Min Act: -0.0000

Data Index: 545250 (The Pile)

Max Activating Token Index: 619

Text #10

Max Range: 1.6940. Min Range: -1.6940

Max Act: 0.8887. Min Act: -0.0000

Data Index: 1486560 (The Pile)

Max Activating Token Index: 716

Text #11

Max Range: 1.6940. Min Range: -1.6940

Max Act: 1.0590. Min Act: -0.0000

Data Index: 1797622 (The Pile)

Max Activating Token Index: 729

Text #12

Max Range: 1.6940. Min Range: -1.6940

Max Act: 0.8269. Min Act: -0.0000

Data Index: 570388 (The Pile)

Max Activating Token Index: 177

Text #13

Max Range: 1.6940. Min Range: -1.6940

Max Act: 0.8320. Min Act: -0.0000

Data Index: 1249661 (The Pile)

Max Activating Token Index: 298

Text #14

Max Range: 1.6940. Min Range: -1.6940

Max Act: 0.7370. Min Act: -0.0000

Data Index: 1531422 (The Pile)

Max Activating Token Index: 552

Text #15

Max Range: 1.6940. Min Range: -1.6940

Max Act: 0.6274. Min Act: -0.0000

Data Index: 1837862 (The Pile)

Max Activating Token Index: 721

Text #16

Max Range: 1.6940. Min Range: -1.6940

Max Act: 0.8182. Min Act: -0.0000

Data Index: 243191 (The Pile)

Max Activating Token Index: 146

Text #17

Max Range: 1.6940. Min Range: -1.6940

Max Act: 0.7499. Min Act: -0.0000

Data Index: 698851 (The Pile)

Max Activating Token Index: 484

Text #18

Max Range: 1.6940. Min Range: -1.6940

Max Act: 0.7172. Min Act: -0.0000

Data Index: 498176 (The Pile)

Max Activating Token Index: 230

Text #19

Max Range: 1.6940. Min Range: -1.6940

Max Act: 0.6973. Min Act: -0.0000

Data Index: 1819776 (The Pile)

Max Activating Token Index: 479