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

Dataset: The Pile

Neuron 418 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: 0.1973. Min Range: -0.1973

Max Act: 0.1794. Min Act: -0.0000

Data Index: 263882 (The Pile)

Max Activating Token Index: 755

Text #1

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1973. Min Act: -0.0000

Data Index: 571202 (The Pile)

Max Activating Token Index: 537

Text #2

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1757. Min Act: -0.0000

Data Index: 121179 (The Pile)

Max Activating Token Index: 282

Text #3

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1775. Min Act: -0.0000

Data Index: 1242061 (The Pile)

Max Activating Token Index: 62

Text #4

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1309. Min Act: -0.0000

Data Index: 266231 (The Pile)

Max Activating Token Index: 566

Text #5

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1734. Min Act: -0.0000

Data Index: 210636 (The Pile)

Max Activating Token Index: 392

Text #6

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1594. Min Act: -0.0000

Data Index: 1349122 (The Pile)

Max Activating Token Index: 614

Text #7

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1540. Min Act: -0.0000

Data Index: 442199 (The Pile)

Max Activating Token Index: 247

Text #8

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1516. Min Act: -0.0000

Data Index: 821795 (The Pile)

Max Activating Token Index: 105

Text #9

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1454. Min Act: -0.0000

Data Index: 1328629 (The Pile)

Max Activating Token Index: 93

Text #10

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1490. Min Act: -0.0000

Data Index: 1632379 (The Pile)

Max Activating Token Index: 631

Text #11

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.0901. Min Act: -0.0000

Data Index: 28645 (The Pile)

Max Activating Token Index: 968

Text #12

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1528. Min Act: -0.0000

Data Index: 519801 (The Pile)

Max Activating Token Index: 7

Text #13

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1363. Min Act: -0.0000

Data Index: 447481 (The Pile)

Max Activating Token Index: 791

Text #14

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1355. Min Act: -0.0000

Data Index: 401528 (The Pile)

Max Activating Token Index: 767

Text #15

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1397. Min Act: -0.0000

Data Index: 468274 (The Pile)

Max Activating Token Index: 771

Text #16

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1544. Min Act: -0.0000

Data Index: 339265 (The Pile)

Max Activating Token Index: 27

Text #17

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1222. Min Act: -0.0000

Data Index: 917933 (The Pile)

Max Activating Token Index: 60

Text #18

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1284. Min Act: -0.0000

Data Index: 1648359 (The Pile)

Max Activating Token Index: 382

Text #19

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1342. Min Act: -0.0000

Data Index: 1525753 (The Pile)

Max Activating Token Index: 50