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

Dataset: The Pile

Neuron 3401 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: 1.3412. Min Range: -1.3412

Max Act: 1.3412. Min Act: -0.0000

Data Index: 371478 (The Pile)

Max Activating Token Index: 129

Text #1

Max Range: 1.3412. Min Range: -1.3412

Max Act: 1.1021. Min Act: -0.0000

Data Index: 1165294 (The Pile)

Max Activating Token Index: 642

Text #2

Max Range: 1.3412. Min Range: -1.3412

Max Act: 0.8624. Min Act: -0.0000

Data Index: 1331010 (The Pile)

Max Activating Token Index: 395

Text #3

Max Range: 1.3412. Min Range: -1.3412

Max Act: 0.8911. Min Act: -0.0000

Data Index: 1111979 (The Pile)

Max Activating Token Index: 151

Text #4

Max Range: 1.3412. Min Range: -1.3412

Max Act: 0.8644. Min Act: -0.0000

Data Index: 867149 (The Pile)

Max Activating Token Index: 96

Text #5

Max Range: 1.3412. Min Range: -1.3412

Max Act: 0.7711. Min Act: -0.0000

Data Index: 1946212 (The Pile)

Max Activating Token Index: 154

Text #6

Max Range: 1.3412. Min Range: -1.3412

Max Act: 0.8207. Min Act: -0.0000

Data Index: 1634452 (The Pile)

Max Activating Token Index: 32

Text #7

Max Range: 1.3412. Min Range: -1.3412

Max Act: 0.8124. Min Act: -0.0000

Data Index: 1753192 (The Pile)

Max Activating Token Index: 51

Text #8

Max Range: 1.3412. Min Range: -1.3412

Max Act: 0.7558. Min Act: -0.0000

Data Index: 1646216 (The Pile)

Max Activating Token Index: 571

Text #9

Max Range: 1.3412. Min Range: -1.3412

Max Act: 0.7486. Min Act: -0.0000

Data Index: 1392788 (The Pile)

Max Activating Token Index: 22

Text #10

Max Range: 1.3412. Min Range: -1.3412

Max Act: 0.7235. Min Act: -0.0000

Data Index: 1406539 (The Pile)

Max Activating Token Index: 100

Text #11

Max Range: 1.3412. Min Range: -1.3412

Max Act: 0.6434. Min Act: -0.0000

Data Index: 1173405 (The Pile)

Max Activating Token Index: 807

Text #12

Max Range: 1.3412. Min Range: -1.3412

Max Act: 0.6876. Min Act: -0.0000

Data Index: 935820 (The Pile)

Max Activating Token Index: 715

Text #13

Max Range: 1.3412. Min Range: -1.3412

Max Act: 0.7053. Min Act: -0.0000

Data Index: 1361778 (The Pile)

Max Activating Token Index: 32

Text #14

Max Range: 1.3412. Min Range: -1.3412

Max Act: 0.6733. Min Act: -0.0000

Data Index: 466532 (The Pile)

Max Activating Token Index: 887

Text #15

Max Range: 1.3412. Min Range: -1.3412

Max Act: 0.7142. Min Act: -0.0000

Data Index: 1251869 (The Pile)

Max Activating Token Index: 779

Text #16

Max Range: 1.3412. Min Range: -1.3412

Max Act: 0.6815. Min Act: -0.0000

Data Index: 1397674 (The Pile)

Max Activating Token Index: 1006

Text #17

Max Range: 1.3412. Min Range: -1.3412

Max Act: 0.7278. Min Act: -0.0000

Data Index: 59379 (The Pile)

Max Activating Token Index: 270

Text #18

Max Range: 1.3412. Min Range: -1.3412

Max Act: 0.6322. Min Act: -0.0000

Data Index: 937877 (The Pile)

Max Activating Token Index: 655

Text #19

Max Range: 1.3412. Min Range: -1.3412

Max Act: 0.6901. Min Act: -0.0000

Data Index: 58057 (The Pile)

Max Activating Token Index: 415