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

Dataset: The Pile

Neuron 3732 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.4721. Min Act: -0.0000

Data Index: 1765759 (The Pile)

Max Activating Token Index: 373

Text #1

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.4541. Min Act: -0.0000

Data Index: 1971295 (The Pile)

Max Activating Token Index: 580

Text #2

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.4623. Min Act: -0.0000

Data Index: 1996546 (The Pile)

Max Activating Token Index: 756

Text #3

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.4130. Min Act: -0.0000

Data Index: 727003 (The Pile)

Max Activating Token Index: 841

Text #4

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3788. Min Act: -0.0000

Data Index: 1598598 (The Pile)

Max Activating Token Index: 251

Text #5

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3743. Min Act: -0.0000

Data Index: 621938 (The Pile)

Max Activating Token Index: 746

Text #6

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3710. Min Act: -0.0000

Data Index: 717901 (The Pile)

Max Activating Token Index: 258

Text #7

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3509. Min Act: -0.0000

Data Index: 568972 (The Pile)

Max Activating Token Index: 452

Text #8

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.2940. Min Act: -0.0000

Data Index: 399989 (The Pile)

Max Activating Token Index: 830

Text #9

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3227. Min Act: -0.0000

Data Index: 1779777 (The Pile)

Max Activating Token Index: 1020

Text #10

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3458. Min Act: -0.0000

Data Index: 627244 (The Pile)

Max Activating Token Index: 31

Text #11

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3053. Min Act: -0.0000

Data Index: 334844 (The Pile)

Max Activating Token Index: 982

Text #12

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3315. Min Act: -0.0000

Data Index: 887294 (The Pile)

Max Activating Token Index: 258

Text #13

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3347. Min Act: -0.0000

Data Index: 1474156 (The Pile)

Max Activating Token Index: 354

Text #14

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3235. Min Act: -0.0000

Data Index: 1541706 (The Pile)

Max Activating Token Index: 278

Text #15

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.2892. Min Act: -0.0000

Data Index: 311226 (The Pile)

Max Activating Token Index: 804

Text #16

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3134. Min Act: -0.0000

Data Index: 1415779 (The Pile)

Max Activating Token Index: 339

Text #17

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.2815. Min Act: -0.0000

Data Index: 1405035 (The Pile)

Max Activating Token Index: 417

Text #18

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.2690. Min Act: -0.0000

Data Index: 1542920 (The Pile)

Max Activating Token Index: 936

Text #19

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.2868. Min Act: -0.0000

Data Index: 1806120 (The Pile)

Max Activating Token Index: 855