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

Dataset: The Pile

Neuron 1538 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: 0.2161. Min Range: -0.2161

Max Act: 0.2161. Min Act: -0.0000

Data Index: 271119 (The Pile)

Max Activating Token Index: 234

Text #1

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1659. Min Act: -0.0000

Data Index: 1001416 (The Pile)

Max Activating Token Index: 939

Text #2

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1316. Min Act: -0.0000

Data Index: 1642153 (The Pile)

Max Activating Token Index: 659

Text #3

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1820. Min Act: -0.0000

Data Index: 1795855 (The Pile)

Max Activating Token Index: 480

Text #4

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1562. Min Act: -0.0000

Data Index: 157119 (The Pile)

Max Activating Token Index: 509

Text #5

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1426. Min Act: -0.0000

Data Index: 1205792 (The Pile)

Max Activating Token Index: 969

Text #6

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1447. Min Act: -0.0000

Data Index: 1973886 (The Pile)

Max Activating Token Index: 863

Text #7

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1486. Min Act: -0.0000

Data Index: 194208 (The Pile)

Max Activating Token Index: 83

Text #8

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1525. Min Act: -0.0000

Data Index: 1151292 (The Pile)

Max Activating Token Index: 76

Text #9

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1452. Min Act: -0.0000

Data Index: 1786350 (The Pile)

Max Activating Token Index: 493

Text #10

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1562. Min Act: -0.0000

Data Index: 842907 (The Pile)

Max Activating Token Index: 918

Text #11

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1609. Min Act: -0.0000

Data Index: 1946512 (The Pile)

Max Activating Token Index: 928

Text #12

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1433. Min Act: -0.0000

Data Index: 2248 (The Pile)

Max Activating Token Index: 314

Text #13

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1325. Min Act: -0.0000

Data Index: 1654529 (The Pile)

Max Activating Token Index: 254

Text #14

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1116. Min Act: -0.0000

Data Index: 1610263 (The Pile)

Max Activating Token Index: 358

Text #15

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1167. Min Act: -0.0000

Data Index: 740993 (The Pile)

Max Activating Token Index: 941

Text #16

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1285. Min Act: -0.0000

Data Index: 841117 (The Pile)

Max Activating Token Index: 398

Text #17

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1483. Min Act: -0.0000

Data Index: 1243539 (The Pile)

Max Activating Token Index: 438

Text #18

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1241. Min Act: -0.0000

Data Index: 843512 (The Pile)

Max Activating Token Index: 123

Text #19

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1310. Min Act: -0.0000

Data Index: 1897722 (The Pile)

Max Activating Token Index: 460