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

Dataset: The Pile

Neuron 3200 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.3799. Min Act: -0.0000

Data Index: 1066662 (The Pile)

Max Activating Token Index: 107

Text #1

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.3407. Min Act: -0.0000

Data Index: 147940 (The Pile)

Max Activating Token Index: 97

Text #2

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.3722. Min Act: -0.0000

Data Index: 1725668 (The Pile)

Max Activating Token Index: 294

Text #3

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.4522. Min Act: -0.0000

Data Index: 1462047 (The Pile)

Max Activating Token Index: 1015

Text #4

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.2858. Min Act: -0.0000

Data Index: 151801 (The Pile)

Max Activating Token Index: 593

Text #5

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.2049. Min Act: -0.0000

Data Index: 376482 (The Pile)

Max Activating Token Index: 798

Text #6

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.2750. Min Act: -0.0000

Data Index: 1430536 (The Pile)

Max Activating Token Index: 46

Text #7

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.4224. Min Act: -0.0000

Data Index: 220333 (The Pile)

Max Activating Token Index: 940

Text #8

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.2263. Min Act: -0.0000

Data Index: 580272 (The Pile)

Max Activating Token Index: 874

Text #9

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.4171. Min Act: -0.0000

Data Index: 1179601 (The Pile)

Max Activating Token Index: 269

Text #10

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.2790. Min Act: -0.0000

Data Index: 452203 (The Pile)

Max Activating Token Index: 887

Text #11

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.1012. Min Act: -0.0000

Data Index: 1389804 (The Pile)

Max Activating Token Index: 920

Text #12

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.2315. Min Act: -0.0000

Data Index: 1889860 (The Pile)

Max Activating Token Index: 881

Text #13

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.2036. Min Act: -0.0000

Data Index: 1039622 (The Pile)

Max Activating Token Index: 278

Text #14

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.2388. Min Act: -0.0000

Data Index: 1922805 (The Pile)

Max Activating Token Index: 250

Text #15

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.2837. Min Act: -0.0000

Data Index: 28872 (The Pile)

Max Activating Token Index: 96

Text #16

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.1345. Min Act: -0.0000

Data Index: 1119714 (The Pile)

Max Activating Token Index: 761

Text #17

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.2053. Min Act: -0.0000

Data Index: 1811551 (The Pile)

Max Activating Token Index: 503

Text #18

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.1713. Min Act: -0.0000

Data Index: 1661408 (The Pile)

Max Activating Token Index: 839

Text #19

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.2874. Min Act: -0.0000

Data Index: 1691610 (The Pile)

Max Activating Token Index: 224