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

Dataset: The Pile

Neuron 3748 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.5529. Min Act: -0.0000

Data Index: 1400584 (The Pile)

Max Activating Token Index: 227

Text #1

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.5473. Min Act: -0.0000

Data Index: 1421382 (The Pile)

Max Activating Token Index: 822

Text #2

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.5375. Min Act: -0.0000

Data Index: 1682566 (The Pile)

Max Activating Token Index: 321

Text #3

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.4731. Min Act: -0.0000

Data Index: 1461554 (The Pile)

Max Activating Token Index: 631

Text #4

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.4984. Min Act: -0.0000

Data Index: 1191838 (The Pile)

Max Activating Token Index: 561

Text #5

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.4920. Min Act: -0.0000

Data Index: 1866618 (The Pile)

Max Activating Token Index: 438

Text #6

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.4929. Min Act: -0.0000

Data Index: 1521470 (The Pile)

Max Activating Token Index: 463

Text #7

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.4401. Min Act: -0.0000

Data Index: 1498251 (The Pile)

Max Activating Token Index: 677

Text #8

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.4432. Min Act: -0.0000

Data Index: 882852 (The Pile)

Max Activating Token Index: 787

Text #9

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.4886. Min Act: -0.0000

Data Index: 523670 (The Pile)

Max Activating Token Index: 876

Text #10

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.4500. Min Act: -0.0000

Data Index: 760136 (The Pile)

Max Activating Token Index: 538

Text #11

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.4493. Min Act: -0.0000

Data Index: 1836496 (The Pile)

Max Activating Token Index: 270

Text #12

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.5278. Min Act: -0.0000

Data Index: 589283 (The Pile)

Max Activating Token Index: 111

Text #13

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.4601. Min Act: -0.0000

Data Index: 709948 (The Pile)

Max Activating Token Index: 303

Text #14

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.4475. Min Act: -0.0000

Data Index: 447719 (The Pile)

Max Activating Token Index: 942

Text #15

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.4130. Min Act: -0.0000

Data Index: 518114 (The Pile)

Max Activating Token Index: 342

Text #16

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.4500. Min Act: -0.0000

Data Index: 596219 (The Pile)

Max Activating Token Index: 64

Text #17

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.3879. Min Act: -0.0000

Data Index: 152956 (The Pile)

Max Activating Token Index: 761

Text #18

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.4272. Min Act: -0.0000

Data Index: 430013 (The Pile)

Max Activating Token Index: 284

Text #19

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.4413. Min Act: -0.0000

Data Index: 1326890 (The Pile)

Max Activating Token Index: 536