Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3547 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0030. Min Range: -1.0030

Max Act: 1.0030. Min Act: -0.0000

Data Index: 1197521 (The Pile)

Max Activating Token Index: 964

Text #1

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.8733. Min Act: -0.0000

Data Index: 965716 (The Pile)

Max Activating Token Index: 362

Text #2

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.8230. Min Act: -0.0000

Data Index: 18931 (The Pile)

Max Activating Token Index: 1005

Text #3

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.7699. Min Act: -0.0000

Data Index: 1915616 (The Pile)

Max Activating Token Index: 914

Text #4

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.7567. Min Act: -0.0000

Data Index: 331445 (The Pile)

Max Activating Token Index: 909

Text #5

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.7367. Min Act: -0.0000

Data Index: 1359860 (The Pile)

Max Activating Token Index: 434

Text #6

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.7501. Min Act: -0.0000

Data Index: 1098457 (The Pile)

Max Activating Token Index: 551

Text #7

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.6830. Min Act: -0.0000

Data Index: 1745130 (The Pile)

Max Activating Token Index: 782

Text #8

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.7194. Min Act: -0.0000

Data Index: 1375636 (The Pile)

Max Activating Token Index: 581

Text #9

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.7342. Min Act: -0.0000

Data Index: 887947 (The Pile)

Max Activating Token Index: 909

Text #10

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.6783. Min Act: -0.0000

Data Index: 603043 (The Pile)

Max Activating Token Index: 421

Text #11

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.7209. Min Act: -0.0000

Data Index: 1913586 (The Pile)

Max Activating Token Index: 373

Text #12

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.6710. Min Act: -0.0000

Data Index: 1834767 (The Pile)

Max Activating Token Index: 992

Text #13

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.7138. Min Act: -0.0000

Data Index: 426425 (The Pile)

Max Activating Token Index: 163

Text #14

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.6437. Min Act: -0.0000

Data Index: 1053791 (The Pile)

Max Activating Token Index: 392

Text #15

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.6616. Min Act: -0.0000

Data Index: 1262472 (The Pile)

Max Activating Token Index: 515

Text #16

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.6839. Min Act: -0.0000

Data Index: 1221736 (The Pile)

Max Activating Token Index: 931

Text #17

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.6827. Min Act: -0.0000

Data Index: 1362311 (The Pile)

Max Activating Token Index: 402

Text #18

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.6961. Min Act: -0.0000

Data Index: 24505 (The Pile)

Max Activating Token Index: 122

Text #19

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.6715. Min Act: -0.0000

Data Index: 1518198 (The Pile)

Max Activating Token Index: 926