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

Dataset: The Pile

Neuron 3124 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: 7.2793. Min Range: -7.2793

Max Act: 7.2793. Min Act: -0.0000

Data Index: 1321362 (The Pile)

Max Activating Token Index: 759

Text #1

Max Range: 7.2793. Min Range: -7.2793

Max Act: 7.0415. Min Act: -0.0000

Data Index: 1165585 (The Pile)

Max Activating Token Index: 474

Text #2

Max Range: 7.2793. Min Range: -7.2793

Max Act: 6.4206. Min Act: -0.0000

Data Index: 736155 (The Pile)

Max Activating Token Index: 703

Text #3

Max Range: 7.2793. Min Range: -7.2793

Max Act: 6.9654. Min Act: -0.0000

Data Index: 125699 (The Pile)

Max Activating Token Index: 366

Text #4

Max Range: 7.2793. Min Range: -7.2793

Max Act: 6.9620. Min Act: -0.0000

Data Index: 360059 (The Pile)

Max Activating Token Index: 241

Text #5

Max Range: 7.2793. Min Range: -7.2793

Max Act: 6.8988. Min Act: -0.0000

Data Index: 1264750 (The Pile)

Max Activating Token Index: 689

Text #6

Max Range: 7.2793. Min Range: -7.2793

Max Act: 6.8877. Min Act: -0.0000

Data Index: 1137904 (The Pile)

Max Activating Token Index: 475

Text #7

Max Range: 7.2793. Min Range: -7.2793

Max Act: 7.1427. Min Act: -0.0000

Data Index: 992683 (The Pile)

Max Activating Token Index: 811

Text #8

Max Range: 7.2793. Min Range: -7.2793

Max Act: 6.6346. Min Act: -0.0000

Data Index: 383822 (The Pile)

Max Activating Token Index: 811

Text #9

Max Range: 7.2793. Min Range: -7.2793

Max Act: 6.7939. Min Act: -0.0000

Data Index: 460066 (The Pile)

Max Activating Token Index: 968

Text #10

Max Range: 7.2793. Min Range: -7.2793

Max Act: 6.7406. Min Act: -0.0000

Data Index: 240572 (The Pile)

Max Activating Token Index: 860

Text #11

Max Range: 7.2793. Min Range: -7.2793

Max Act: 6.6825. Min Act: -0.0000

Data Index: 1960347 (The Pile)

Max Activating Token Index: 468

Text #12

Max Range: 7.2793. Min Range: -7.2793

Max Act: 6.6514. Min Act: -0.0000

Data Index: 920557 (The Pile)

Max Activating Token Index: 943

Text #13

Max Range: 7.2793. Min Range: -7.2793

Max Act: 6.6397. Min Act: -0.0000

Data Index: 681509 (The Pile)

Max Activating Token Index: 461

Text #14

Max Range: 7.2793. Min Range: -7.2793

Max Act: 6.6220. Min Act: -0.0000

Data Index: 1331308 (The Pile)

Max Activating Token Index: 351

Text #15

Max Range: 7.2793. Min Range: -7.2793

Max Act: 6.6144. Min Act: -0.0000

Data Index: 1770490 (The Pile)

Max Activating Token Index: 591

Text #16

Max Range: 7.2793. Min Range: -7.2793

Max Act: 6.5994. Min Act: -0.0000

Data Index: 1597614 (The Pile)

Max Activating Token Index: 562

Text #17

Max Range: 7.2793. Min Range: -7.2793

Max Act: 6.4064. Min Act: -0.0001

Data Index: 1205131 (The Pile)

Max Activating Token Index: 857

Text #18

Max Range: 7.2793. Min Range: -7.2793

Max Act: 6.3167. Min Act: -0.0001

Data Index: 1235609 (The Pile)

Max Activating Token Index: 631

Text #19

Max Range: 7.2793. Min Range: -7.2793

Max Act: 6.4713. Min Act: -0.0000

Data Index: 1098821 (The Pile)

Max Activating Token Index: 535