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

Dataset: The Pile

Neuron 1784 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2115. Min Range: -1.2115

Max Act: 1.1908. Min Act: -0.0000

Data Index: 812750 (The Pile)

Max Activating Token Index: 533

Text #1

Max Range: 1.2115. Min Range: -1.2115

Max Act: 1.2115. Min Act: -0.0000

Data Index: 299017 (The Pile)

Max Activating Token Index: 592

Text #2

Max Range: 1.2115. Min Range: -1.2115

Max Act: 1.0723. Min Act: -0.0000

Data Index: 746616 (The Pile)

Max Activating Token Index: 718

Text #3

Max Range: 1.2115. Min Range: -1.2115

Max Act: 1.1253. Min Act: -0.0000

Data Index: 1801466 (The Pile)

Max Activating Token Index: 23

Text #4

Max Range: 1.2115. Min Range: -1.2115

Max Act: 1.1327. Min Act: -0.0000

Data Index: 1137339 (The Pile)

Max Activating Token Index: 563

Text #5

Max Range: 1.2115. Min Range: -1.2115

Max Act: 1.1265. Min Act: -0.0000

Data Index: 652455 (The Pile)

Max Activating Token Index: 480

Text #6

Max Range: 1.2115. Min Range: -1.2115

Max Act: 1.0759. Min Act: -0.0000

Data Index: 515622 (The Pile)

Max Activating Token Index: 918

Text #7

Max Range: 1.2115. Min Range: -1.2115

Max Act: 1.1610. Min Act: -0.0000

Data Index: 87753 (The Pile)

Max Activating Token Index: 604

Text #8

Max Range: 1.2115. Min Range: -1.2115

Max Act: 0.8005. Min Act: -0.0000

Data Index: 1619919 (The Pile)

Max Activating Token Index: 57

Text #9

Max Range: 1.2115. Min Range: -1.2115

Max Act: 0.8241. Min Act: -0.0000

Data Index: 1519137 (The Pile)

Max Activating Token Index: 423

Text #10

Max Range: 1.2115. Min Range: -1.2115

Max Act: 0.7641. Min Act: -0.0000

Data Index: 1184945 (The Pile)

Max Activating Token Index: 694

Text #11

Max Range: 1.2115. Min Range: -1.2115

Max Act: 0.7078. Min Act: -0.0000

Data Index: 1520159 (The Pile)

Max Activating Token Index: 327

Text #12

Max Range: 1.2115. Min Range: -1.2115

Max Act: 0.7071. Min Act: -0.0000

Data Index: 363216 (The Pile)

Max Activating Token Index: 999

Text #13

Max Range: 1.2115. Min Range: -1.2115

Max Act: 0.7413. Min Act: -0.0000

Data Index: 1842853 (The Pile)

Max Activating Token Index: 484

Text #14

Max Range: 1.2115. Min Range: -1.2115

Max Act: 0.7463. Min Act: -0.0000

Data Index: 670632 (The Pile)

Max Activating Token Index: 983

Text #15

Max Range: 1.2115. Min Range: -1.2115

Max Act: 0.7351. Min Act: -0.0000

Data Index: 1238105 (The Pile)

Max Activating Token Index: 142

Text #16

Max Range: 1.2115. Min Range: -1.2115

Max Act: 0.6730. Min Act: -0.0000

Data Index: 224258 (The Pile)

Max Activating Token Index: 35

Text #17

Max Range: 1.2115. Min Range: -1.2115

Max Act: 0.6509. Min Act: -0.0000

Data Index: 36661 (The Pile)

Max Activating Token Index: 540

Text #18

Max Range: 1.2115. Min Range: -1.2115

Max Act: 0.6504. Min Act: -0.0000

Data Index: 1307994 (The Pile)

Max Activating Token Index: 591

Text #19

Max Range: 1.2115. Min Range: -1.2115

Max Act: 0.6379. Min Act: -0.0000

Data Index: 894081 (The Pile)

Max Activating Token Index: 852