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

Dataset: The Pile

Neuron 4246 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: 0.9293. Min Range: -0.9293

Max Act: 0.9293. Min Act: -0.0000

Data Index: 201801 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.9293. Min Range: -0.9293

Max Act: 0.7729. Min Act: -0.0000

Data Index: 350955 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.9293. Min Range: -0.9293

Max Act: 0.7394. Min Act: -0.0000

Data Index: 1530037 (The Pile)

Max Activating Token Index: 749

Text #3

Max Range: 0.9293. Min Range: -0.9293

Max Act: 0.7266. Min Act: -0.0000

Data Index: 1140917 (The Pile)

Max Activating Token Index: 1003

Text #4

Max Range: 0.9293. Min Range: -0.9293

Max Act: 0.6173. Min Act: -0.0000

Data Index: 189753 (The Pile)

Max Activating Token Index: 732

Text #5

Max Range: 0.9293. Min Range: -0.9293

Max Act: 0.6488. Min Act: -0.0000

Data Index: 1863340 (The Pile)

Max Activating Token Index: 902

Text #6

Max Range: 0.9293. Min Range: -0.9293

Max Act: 0.6418. Min Act: -0.0000

Data Index: 87643 (The Pile)

Max Activating Token Index: 396

Text #7

Max Range: 0.9293. Min Range: -0.9293

Max Act: 0.5976. Min Act: -0.0000

Data Index: 455108 (The Pile)

Max Activating Token Index: 31

Text #8

Max Range: 0.9293. Min Range: -0.9293

Max Act: 0.5746. Min Act: -0.0000

Data Index: 333781 (The Pile)

Max Activating Token Index: 773

Text #9

Max Range: 0.9293. Min Range: -0.9293

Max Act: 0.5724. Min Act: -0.0000

Data Index: 525793 (The Pile)

Max Activating Token Index: 963

Text #10

Max Range: 0.9293. Min Range: -0.9293

Max Act: 0.6096. Min Act: -0.0000

Data Index: 1049217 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.9293. Min Range: -0.9293

Max Act: 0.5817. Min Act: -0.0000

Data Index: 898372 (The Pile)

Max Activating Token Index: 243

Text #12

Max Range: 0.9293. Min Range: -0.9293

Max Act: 0.5905. Min Act: -0.0000

Data Index: 1850976 (The Pile)

Max Activating Token Index: 41

Text #13

Max Range: 0.9293. Min Range: -0.9293

Max Act: 0.5533. Min Act: -0.0000

Data Index: 620221 (The Pile)

Max Activating Token Index: 493

Text #14

Max Range: 0.9293. Min Range: -0.9293

Max Act: 0.5828. Min Act: -0.0000

Data Index: 1165495 (The Pile)

Max Activating Token Index: 552

Text #15

Max Range: 0.9293. Min Range: -0.9293

Max Act: 0.5929. Min Act: -0.0000

Data Index: 247872 (The Pile)

Max Activating Token Index: 670

Text #16

Max Range: 0.9293. Min Range: -0.9293

Max Act: 0.5731. Min Act: -0.0000

Data Index: 68310 (The Pile)

Max Activating Token Index: 213

Text #17

Max Range: 0.9293. Min Range: -0.9293

Max Act: 0.5567. Min Act: -0.0000

Data Index: 949118 (The Pile)

Max Activating Token Index: 309

Text #18

Max Range: 0.9293. Min Range: -0.9293

Max Act: 0.5911. Min Act: -0.0000

Data Index: 335042 (The Pile)

Max Activating Token Index: 746

Text #19

Max Range: 0.9293. Min Range: -0.9293

Max Act: 0.5740. Min Act: -0.0000

Data Index: 1389209 (The Pile)

Max Activating Token Index: 749