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

Dataset: The Pile

Neuron 2320 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: 0.8731. Min Range: -0.8731

Max Act: 0.8731. Min Act: -0.0000

Data Index: 1893119 (The Pile)

Max Activating Token Index: 435

Text #1

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.8687. Min Act: 0.0000

Data Index: 631762 (The Pile)

Max Activating Token Index: 522

Text #2

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.7625. Min Act: 0.0000

Data Index: 1175746 (The Pile)

Max Activating Token Index: 333

Text #3

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.7849. Min Act: -0.0000

Data Index: 898581 (The Pile)

Max Activating Token Index: 815

Text #4

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.7562. Min Act: -0.0000

Data Index: 1770304 (The Pile)

Max Activating Token Index: 236

Text #5

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.7543. Min Act: -0.0000

Data Index: 1683973 (The Pile)

Max Activating Token Index: 961

Text #6

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.7057. Min Act: -0.0000

Data Index: 1844392 (The Pile)

Max Activating Token Index: 892

Text #7

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.6924. Min Act: -0.0000

Data Index: 516313 (The Pile)

Max Activating Token Index: 344

Text #8

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.7008. Min Act: -0.0000

Data Index: 893887 (The Pile)

Max Activating Token Index: 144

Text #9

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.6480. Min Act: 0.0000

Data Index: 1169416 (The Pile)

Max Activating Token Index: 309

Text #10

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.6112. Min Act: 0.0000

Data Index: 1474020 (The Pile)

Max Activating Token Index: 39

Text #11

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.5916. Min Act: 0.0000

Data Index: 1854097 (The Pile)

Max Activating Token Index: 437

Text #12

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.5627. Min Act: -0.0000

Data Index: 1831338 (The Pile)

Max Activating Token Index: 247

Text #13

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.5658. Min Act: -0.0000

Data Index: 1995409 (The Pile)

Max Activating Token Index: 978

Text #14

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.5420. Min Act: -0.0000

Data Index: 530361 (The Pile)

Max Activating Token Index: 795

Text #15

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.5706. Min Act: 0.0000

Data Index: 1961277 (The Pile)

Max Activating Token Index: 158

Text #16

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.5434. Min Act: -0.0000

Data Index: 1520650 (The Pile)

Max Activating Token Index: 479

Text #17

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.4931. Min Act: 0.0000

Data Index: 1515755 (The Pile)

Max Activating Token Index: 105

Text #18

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.5208. Min Act: -0.0000

Data Index: 1730261 (The Pile)

Max Activating Token Index: 555

Text #19

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.4686. Min Act: 0.0000

Data Index: 1110716 (The Pile)

Max Activating Token Index: 808