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

Dataset: The Pile

Neuron 2301 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.2204. Min Act: -0.0000

Data Index: 157460 (The Pile)

Max Activating Token Index: 90

Text #1

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.2152. Min Act: -0.0000

Data Index: 514398 (The Pile)

Max Activating Token Index: 142

Text #2

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.2087. Min Act: -0.0000

Data Index: 1809519 (The Pile)

Max Activating Token Index: 880

Text #3

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.2044. Min Act: -0.0000

Data Index: 363236 (The Pile)

Max Activating Token Index: 540

Text #4

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.1822. Min Act: -0.0000

Data Index: 758587 (The Pile)

Max Activating Token Index: 676

Text #5

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.1877. Min Act: -0.0000

Data Index: 1400848 (The Pile)

Max Activating Token Index: 80

Text #6

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.1813. Min Act: -0.0000

Data Index: 1132660 (The Pile)

Max Activating Token Index: 452

Text #7

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.1745. Min Act: -0.0000

Data Index: 515376 (The Pile)

Max Activating Token Index: 64

Text #8

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.1716. Min Act: -0.0000

Data Index: 337572 (The Pile)

Max Activating Token Index: 848

Text #9

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.1763. Min Act: -0.0000

Data Index: 1905446 (The Pile)

Max Activating Token Index: 381

Text #10

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.1802. Min Act: -0.0000

Data Index: 1501518 (The Pile)

Max Activating Token Index: 132

Text #11

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.1823. Min Act: -0.0000

Data Index: 1445805 (The Pile)

Max Activating Token Index: 580

Text #12

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.1642. Min Act: -0.0000

Data Index: 1830679 (The Pile)

Max Activating Token Index: 371

Text #13

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.1581. Min Act: -0.0000

Data Index: 1424219 (The Pile)

Max Activating Token Index: 553

Text #14

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.1654. Min Act: -0.0000

Data Index: 1354408 (The Pile)

Max Activating Token Index: 551

Text #15

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.1578. Min Act: -0.0000

Data Index: 55877 (The Pile)

Max Activating Token Index: 555

Text #16

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.1755. Min Act: -0.0000

Data Index: 110823 (The Pile)

Max Activating Token Index: 862

Text #17

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.1572. Min Act: -0.0000

Data Index: 1075393 (The Pile)

Max Activating Token Index: 256

Text #18

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.1578. Min Act: -0.0000

Data Index: 1791948 (The Pile)

Max Activating Token Index: 379

Text #19

Max Range: 0.2204. Min Range: -0.2204

Max Act: 0.1573. Min Act: -0.0000

Data Index: 1658392 (The Pile)

Max Activating Token Index: 278