Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 772 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.2099. Min Act: -0.0000

Data Index: 766240 (The Pile)

Max Activating Token Index: 348

Text #1

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.2377. Min Act: -0.0000

Data Index: 152348 (The Pile)

Max Activating Token Index: 786

Text #2

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.2228. Min Act: -0.0000

Data Index: 1895237 (The Pile)

Max Activating Token Index: 610

Text #3

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.2065. Min Act: -0.0000

Data Index: 255819 (The Pile)

Max Activating Token Index: 399

Text #4

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.2061. Min Act: -0.0000

Data Index: 632786 (The Pile)

Max Activating Token Index: 249

Text #5

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.1990. Min Act: -0.0000

Data Index: 225844 (The Pile)

Max Activating Token Index: 357

Text #6

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.2046. Min Act: -0.0000

Data Index: 1021991 (The Pile)

Max Activating Token Index: 252

Text #7

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.1941. Min Act: -0.0000

Data Index: 1428458 (The Pile)

Max Activating Token Index: 109

Text #8

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.1773. Min Act: -0.0000

Data Index: 66491 (The Pile)

Max Activating Token Index: 790

Text #9

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.1787. Min Act: -0.0000

Data Index: 352686 (The Pile)

Max Activating Token Index: 157

Text #10

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.1914. Min Act: -0.0000

Data Index: 624164 (The Pile)

Max Activating Token Index: 900

Text #11

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.1783. Min Act: -0.0000

Data Index: 834309 (The Pile)

Max Activating Token Index: 412

Text #12

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.1911. Min Act: -0.0000

Data Index: 615496 (The Pile)

Max Activating Token Index: 146

Text #13

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.1796. Min Act: -0.0000

Data Index: 1615828 (The Pile)

Max Activating Token Index: 372

Text #14

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.1722. Min Act: -0.0000

Data Index: 973133 (The Pile)

Max Activating Token Index: 603

Text #15

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.1607. Min Act: -0.0000

Data Index: 1630306 (The Pile)

Max Activating Token Index: 275

Text #16

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.1631. Min Act: -0.0000

Data Index: 1073941 (The Pile)

Max Activating Token Index: 500

Text #17

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.1562. Min Act: -0.0000

Data Index: 2269 (The Pile)

Max Activating Token Index: 31

Text #18

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.1609. Min Act: -0.0000

Data Index: 11701 (The Pile)

Max Activating Token Index: 20

Text #19

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.1658. Min Act: -0.0000

Data Index: 757710 (The Pile)

Max Activating Token Index: 902