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

Dataset: The Pile

Neuron 3431 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: 0.9616. Min Range: -0.9616

Max Act: 0.9616. Min Act: -0.0000

Data Index: 1248657 (The Pile)

Max Activating Token Index: 321

Text #1

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.7975. Min Act: -0.0000

Data Index: 368444 (The Pile)

Max Activating Token Index: 670

Text #2

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.7338. Min Act: -0.0000

Data Index: 1639812 (The Pile)

Max Activating Token Index: 532

Text #3

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.7684. Min Act: -0.0000

Data Index: 1512480 (The Pile)

Max Activating Token Index: 134

Text #4

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.7678. Min Act: -0.0000

Data Index: 345925 (The Pile)

Max Activating Token Index: 427

Text #5

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.7447. Min Act: -0.0000

Data Index: 846664 (The Pile)

Max Activating Token Index: 458

Text #6

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.6873. Min Act: -0.0000

Data Index: 946392 (The Pile)

Max Activating Token Index: 409

Text #7

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.7085. Min Act: -0.0000

Data Index: 1251826 (The Pile)

Max Activating Token Index: 653

Text #8

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.6655. Min Act: -0.0000

Data Index: 1784439 (The Pile)

Max Activating Token Index: 228

Text #9

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.7121. Min Act: -0.0000

Data Index: 1199927 (The Pile)

Max Activating Token Index: 133

Text #10

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.6487. Min Act: -0.0000

Data Index: 37896 (The Pile)

Max Activating Token Index: 77

Text #11

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.6427. Min Act: -0.0000

Data Index: 1902145 (The Pile)

Max Activating Token Index: 75

Text #12

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.6076. Min Act: -0.0000

Data Index: 1648858 (The Pile)

Max Activating Token Index: 443

Text #13

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.6512. Min Act: -0.0000

Data Index: 1194683 (The Pile)

Max Activating Token Index: 203

Text #14

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.7083. Min Act: -0.0000

Data Index: 1814413 (The Pile)

Max Activating Token Index: 735

Text #15

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.6078. Min Act: -0.0000

Data Index: 1966885 (The Pile)

Max Activating Token Index: 772

Text #16

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.6844. Min Act: -0.0000

Data Index: 1030736 (The Pile)

Max Activating Token Index: 195

Text #17

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.6115. Min Act: -0.0000

Data Index: 1857171 (The Pile)

Max Activating Token Index: 789

Text #18

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.6489. Min Act: -0.0000

Data Index: 711632 (The Pile)

Max Activating Token Index: 695

Text #19

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.6909. Min Act: -0.0000

Data Index: 586946 (The Pile)

Max Activating Token Index: 401