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

Dataset: The Pile

Neuron 3322 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: 1.6771. Min Range: -1.6771

Max Act: 1.6771. Min Act: -0.0000

Data Index: 930131 (The Pile)

Max Activating Token Index: 342

Text #1

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.5164. Min Act: -0.0000

Data Index: 502645 (The Pile)

Max Activating Token Index: 238

Text #2

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.3666. Min Act: -0.0000

Data Index: 64831 (The Pile)

Max Activating Token Index: 385

Text #3

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.3819. Min Act: -0.0000

Data Index: 283301 (The Pile)

Max Activating Token Index: 747

Text #4

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.4520. Min Act: -0.0000

Data Index: 1194267 (The Pile)

Max Activating Token Index: 27

Text #5

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.3353. Min Act: -0.0000

Data Index: 58965 (The Pile)

Max Activating Token Index: 443

Text #6

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.4377. Min Act: -0.0000

Data Index: 981773 (The Pile)

Max Activating Token Index: 886

Text #7

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.4434. Min Act: -0.0000

Data Index: 465775 (The Pile)

Max Activating Token Index: 361

Text #8

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.3018. Min Act: -0.0000

Data Index: 677859 (The Pile)

Max Activating Token Index: 146

Text #9

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.4473. Min Act: -0.0000

Data Index: 1594808 (The Pile)

Max Activating Token Index: 601

Text #10

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.3557. Min Act: -0.0000

Data Index: 886020 (The Pile)

Max Activating Token Index: 24

Text #11

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.2647. Min Act: -0.0000

Data Index: 174530 (The Pile)

Max Activating Token Index: 147

Text #12

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.2259. Min Act: -0.0000

Data Index: 89294 (The Pile)

Max Activating Token Index: 434

Text #13

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.2005. Min Act: -0.0000

Data Index: 1245159 (The Pile)

Max Activating Token Index: 340

Text #14

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.2452. Min Act: -0.0000

Data Index: 1684886 (The Pile)

Max Activating Token Index: 686

Text #15

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.1907. Min Act: -0.0000

Data Index: 1485813 (The Pile)

Max Activating Token Index: 256

Text #16

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.1609. Min Act: -0.0000

Data Index: 899050 (The Pile)

Max Activating Token Index: 1006

Text #17

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.0992. Min Act: -0.0000

Data Index: 1554194 (The Pile)

Max Activating Token Index: 595

Text #18

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.0995. Min Act: -0.0000

Data Index: 1697423 (The Pile)

Max Activating Token Index: 333

Text #19

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.2048. Min Act: -0.0000

Data Index: 1216813 (The Pile)

Max Activating Token Index: 896