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

Dataset: The Pile

Neuron 1676 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: 0.5567. Min Range: -0.5567

Max Act: 0.5567. Min Act: -0.0000

Data Index: 633556 (The Pile)

Max Activating Token Index: 911

Text #1

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.5313. Min Act: -0.0000

Data Index: 1625512 (The Pile)

Max Activating Token Index: 539

Text #2

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.5135. Min Act: -0.0000

Data Index: 1622696 (The Pile)

Max Activating Token Index: 392

Text #3

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.5324. Min Act: -0.0000

Data Index: 881172 (The Pile)

Max Activating Token Index: 400

Text #4

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.5249. Min Act: -0.0000

Data Index: 1231712 (The Pile)

Max Activating Token Index: 402

Text #5

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.5116. Min Act: -0.0000

Data Index: 774225 (The Pile)

Max Activating Token Index: 165

Text #6

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4801. Min Act: -0.0000

Data Index: 207785 (The Pile)

Max Activating Token Index: 722

Text #7

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4742. Min Act: -0.0000

Data Index: 668169 (The Pile)

Max Activating Token Index: 560

Text #8

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4984. Min Act: -0.0000

Data Index: 1874297 (The Pile)

Max Activating Token Index: 607

Text #9

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4588. Min Act: -0.0000

Data Index: 1232930 (The Pile)

Max Activating Token Index: 290

Text #10

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4427. Min Act: -0.0000

Data Index: 170955 (The Pile)

Max Activating Token Index: 301

Text #11

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4517. Min Act: -0.0000

Data Index: 1069111 (The Pile)

Max Activating Token Index: 389

Text #12

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4795. Min Act: -0.0000

Data Index: 1434228 (The Pile)

Max Activating Token Index: 749

Text #13

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4504. Min Act: -0.0000

Data Index: 1673630 (The Pile)

Max Activating Token Index: 412

Text #14

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4304. Min Act: -0.0000

Data Index: 1868579 (The Pile)

Max Activating Token Index: 710

Text #15

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4457. Min Act: -0.0000

Data Index: 491264 (The Pile)

Max Activating Token Index: 400

Text #16

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4741. Min Act: -0.0000

Data Index: 1844542 (The Pile)

Max Activating Token Index: 1000

Text #17

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4657. Min Act: -0.0000

Data Index: 1719005 (The Pile)

Max Activating Token Index: 368

Text #18

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4567. Min Act: -0.0000

Data Index: 1386865 (The Pile)

Max Activating Token Index: 64

Text #19

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4380. Min Act: -0.0000

Data Index: 1868607 (The Pile)

Max Activating Token Index: 444