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

Dataset: The Pile

Neuron 2820 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.9303. Min Act: -0.0000

Data Index: 1356695 (The Pile)

Max Activating Token Index: 379

Text #1

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.8494. Min Act: -0.0000

Data Index: 111345 (The Pile)

Max Activating Token Index: 784

Text #2

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.8155. Min Act: -0.0000

Data Index: 75884 (The Pile)

Max Activating Token Index: 540

Text #3

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.7917. Min Act: -0.0000

Data Index: 256634 (The Pile)

Max Activating Token Index: 114

Text #4

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.7994. Min Act: -0.0000

Data Index: 1707555 (The Pile)

Max Activating Token Index: 772

Text #5

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.7643. Min Act: -0.0000

Data Index: 1300496 (The Pile)

Max Activating Token Index: 433

Text #6

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.7147. Min Act: -0.0000

Data Index: 1135927 (The Pile)

Max Activating Token Index: 505

Text #7

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.7106. Min Act: -0.0000

Data Index: 1395024 (The Pile)

Max Activating Token Index: 760

Text #8

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.7313. Min Act: -0.0000

Data Index: 427006 (The Pile)

Max Activating Token Index: 336

Text #9

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.7563. Min Act: -0.0000

Data Index: 481090 (The Pile)

Max Activating Token Index: 521

Text #10

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.6947. Min Act: -0.0000

Data Index: 1852803 (The Pile)

Max Activating Token Index: 854

Text #11

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.6559. Min Act: -0.0000

Data Index: 201322 (The Pile)

Max Activating Token Index: 411

Text #12

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.6575. Min Act: -0.0000

Data Index: 908791 (The Pile)

Max Activating Token Index: 722

Text #13

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.6315. Min Act: -0.0000

Data Index: 390333 (The Pile)

Max Activating Token Index: 45

Text #14

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.6300. Min Act: -0.0000

Data Index: 1474695 (The Pile)

Max Activating Token Index: 528

Text #15

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.6202. Min Act: -0.0000

Data Index: 940964 (The Pile)

Max Activating Token Index: 343

Text #16

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.6150. Min Act: -0.0000

Data Index: 363202 (The Pile)

Max Activating Token Index: 54

Text #17

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.5996. Min Act: -0.0000

Data Index: 127693 (The Pile)

Max Activating Token Index: 458

Text #18

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.5783. Min Act: -0.0000

Data Index: 1350650 (The Pile)

Max Activating Token Index: 753

Text #19

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.5778. Min Act: -0.0000

Data Index: 1181804 (The Pile)

Max Activating Token Index: 472