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

Dataset: The Pile

Neuron 2912 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2847. Min Range: -4.2847

Max Act: 4.2847. Min Act: -0.0000

Data Index: 1763440 (The Pile)

Max Activating Token Index: 688

Text #1

Max Range: 4.2847. Min Range: -4.2847

Max Act: 3.5462. Min Act: -0.0000

Data Index: 1831959 (The Pile)

Max Activating Token Index: 719

Text #2

Max Range: 4.2847. Min Range: -4.2847

Max Act: 3.4238. Min Act: -0.0000

Data Index: 1147496 (The Pile)

Max Activating Token Index: 784

Text #3

Max Range: 4.2847. Min Range: -4.2847

Max Act: 3.5296. Min Act: -0.0000

Data Index: 1625166 (The Pile)

Max Activating Token Index: 552

Text #4

Max Range: 4.2847. Min Range: -4.2847

Max Act: 3.4876. Min Act: -0.0000

Data Index: 1497898 (The Pile)

Max Activating Token Index: 592

Text #5

Max Range: 4.2847. Min Range: -4.2847

Max Act: 3.4950. Min Act: -0.0000

Data Index: 1751140 (The Pile)

Max Activating Token Index: 686

Text #6

Max Range: 4.2847. Min Range: -4.2847

Max Act: 3.4087. Min Act: -0.0000

Data Index: 1820620 (The Pile)

Max Activating Token Index: 418

Text #7

Max Range: 4.2847. Min Range: -4.2847

Max Act: 3.0960. Min Act: -0.0000

Data Index: 1613879 (The Pile)

Max Activating Token Index: 422

Text #8

Max Range: 4.2847. Min Range: -4.2847

Max Act: 3.3821. Min Act: -0.0000

Data Index: 751393 (The Pile)

Max Activating Token Index: 226

Text #9

Max Range: 4.2847. Min Range: -4.2847

Max Act: 3.3516. Min Act: -0.0000

Data Index: 1993796 (The Pile)

Max Activating Token Index: 477

Text #10

Max Range: 4.2847. Min Range: -4.2847

Max Act: 3.0433. Min Act: -0.0000

Data Index: 327749 (The Pile)

Max Activating Token Index: 992

Text #11

Max Range: 4.2847. Min Range: -4.2847

Max Act: 3.3354. Min Act: -0.0000

Data Index: 383829 (The Pile)

Max Activating Token Index: 983

Text #12

Max Range: 4.2847. Min Range: -4.2847

Max Act: 2.9872. Min Act: -0.0000

Data Index: 620030 (The Pile)

Max Activating Token Index: 71

Text #13

Max Range: 4.2847. Min Range: -4.2847

Max Act: 3.1342. Min Act: -0.0000

Data Index: 1036706 (The Pile)

Max Activating Token Index: 787

Text #14

Max Range: 4.2847. Min Range: -4.2847

Max Act: 3.0847. Min Act: -0.0000

Data Index: 1948108 (The Pile)

Max Activating Token Index: 170

Text #15

Max Range: 4.2847. Min Range: -4.2847

Max Act: 3.2089. Min Act: -0.0000

Data Index: 1436720 (The Pile)

Max Activating Token Index: 1018

Text #16

Max Range: 4.2847. Min Range: -4.2847

Max Act: 3.0243. Min Act: -0.0000

Data Index: 1427710 (The Pile)

Max Activating Token Index: 855

Text #17

Max Range: 4.2847. Min Range: -4.2847

Max Act: 2.8751. Min Act: -0.0000

Data Index: 1290258 (The Pile)

Max Activating Token Index: 334

Text #18

Max Range: 4.2847. Min Range: -4.2847

Max Act: 3.1719. Min Act: -0.0000

Data Index: 172853 (The Pile)

Max Activating Token Index: 268

Text #19

Max Range: 4.2847. Min Range: -4.2847

Max Act: 3.1455. Min Act: -0.0000

Data Index: 295990 (The Pile)

Max Activating Token Index: 666