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

Dataset: The Pile

Neuron 3529 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: 4.4733. Min Range: -4.4733

Max Act: 4.4733. Min Act: -0.0000

Data Index: 1885285 (The Pile)

Max Activating Token Index: 465

Text #1

Max Range: 4.4733. Min Range: -4.4733

Max Act: 4.2561. Min Act: -0.0000

Data Index: 1847727 (The Pile)

Max Activating Token Index: 269

Text #2

Max Range: 4.4733. Min Range: -4.4733

Max Act: 4.1014. Min Act: -0.0000

Data Index: 811028 (The Pile)

Max Activating Token Index: 173

Text #3

Max Range: 4.4733. Min Range: -4.4733

Max Act: 3.9760. Min Act: -0.0000

Data Index: 1529805 (The Pile)

Max Activating Token Index: 962

Text #4

Max Range: 4.4733. Min Range: -4.4733

Max Act: 3.9487. Min Act: -0.0000

Data Index: 378936 (The Pile)

Max Activating Token Index: 935

Text #5

Max Range: 4.4733. Min Range: -4.4733

Max Act: 3.7698. Min Act: -0.0000

Data Index: 141109 (The Pile)

Max Activating Token Index: 469

Text #6

Max Range: 4.4733. Min Range: -4.4733

Max Act: 3.6412. Min Act: -0.0000

Data Index: 1767487 (The Pile)

Max Activating Token Index: 854

Text #7

Max Range: 4.4733. Min Range: -4.4733

Max Act: 3.8058. Min Act: -0.0000

Data Index: 233508 (The Pile)

Max Activating Token Index: 487

Text #8

Max Range: 4.4733. Min Range: -4.4733

Max Act: 3.7597. Min Act: -0.0000

Data Index: 1575945 (The Pile)

Max Activating Token Index: 671

Text #9

Max Range: 4.4733. Min Range: -4.4733

Max Act: 3.5767. Min Act: -0.0000

Data Index: 449586 (The Pile)

Max Activating Token Index: 263

Text #10

Max Range: 4.4733. Min Range: -4.4733

Max Act: 3.7225. Min Act: -0.0000

Data Index: 502499 (The Pile)

Max Activating Token Index: 265

Text #11

Max Range: 4.4733. Min Range: -4.4733

Max Act: 3.8673. Min Act: -0.0000

Data Index: 196427 (The Pile)

Max Activating Token Index: 962

Text #12

Max Range: 4.4733. Min Range: -4.4733

Max Act: 3.7044. Min Act: -0.0000

Data Index: 468627 (The Pile)

Max Activating Token Index: 550

Text #13

Max Range: 4.4733. Min Range: -4.4733

Max Act: 3.6825. Min Act: -0.0000

Data Index: 1824240 (The Pile)

Max Activating Token Index: 120

Text #14

Max Range: 4.4733. Min Range: -4.4733

Max Act: 3.6825. Min Act: -0.0000

Data Index: 1155219 (The Pile)

Max Activating Token Index: 711

Text #15

Max Range: 4.4733. Min Range: -4.4733

Max Act: 3.6614. Min Act: -0.0000

Data Index: 21535 (The Pile)

Max Activating Token Index: 327

Text #16

Max Range: 4.4733. Min Range: -4.4733

Max Act: 3.8193. Min Act: -0.0000

Data Index: 1599695 (The Pile)

Max Activating Token Index: 162

Text #17

Max Range: 4.4733. Min Range: -4.4733

Max Act: 3.6733. Min Act: -0.0000

Data Index: 677658 (The Pile)

Max Activating Token Index: 999

Text #18

Max Range: 4.4733. Min Range: -4.4733

Max Act: 3.8000. Min Act: -0.0000

Data Index: 413089 (The Pile)

Max Activating Token Index: 424

Text #19

Max Range: 4.4733. Min Range: -4.4733

Max Act: 3.6389. Min Act: -0.0000

Data Index: 353223 (The Pile)

Max Activating Token Index: 226