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

Dataset: The Pile

Neuron 3692 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2569. Min Range: -3.2569

Max Act: 3.1296. Min Act: -0.0000

Data Index: 957535 (The Pile)

Max Activating Token Index: 831

Text #1

Max Range: 3.2569. Min Range: -3.2569

Max Act: 3.2569. Min Act: -0.0000

Data Index: 962993 (The Pile)

Max Activating Token Index: 589

Text #2

Max Range: 3.2569. Min Range: -3.2569

Max Act: 3.2539. Min Act: -0.0000

Data Index: 1477899 (The Pile)

Max Activating Token Index: 905

Text #3

Max Range: 3.2569. Min Range: -3.2569

Max Act: 3.0376. Min Act: -0.0000

Data Index: 122815 (The Pile)

Max Activating Token Index: 361

Text #4

Max Range: 3.2569. Min Range: -3.2569

Max Act: 2.9993. Min Act: -0.0000

Data Index: 316286 (The Pile)

Max Activating Token Index: 698

Text #5

Max Range: 3.2569. Min Range: -3.2569

Max Act: 3.1369. Min Act: -0.0000

Data Index: 590310 (The Pile)

Max Activating Token Index: 874

Text #6

Max Range: 3.2569. Min Range: -3.2569

Max Act: 2.9465. Min Act: -0.0000

Data Index: 1827964 (The Pile)

Max Activating Token Index: 682

Text #7

Max Range: 3.2569. Min Range: -3.2569

Max Act: 3.1849. Min Act: -0.0000

Data Index: 1462500 (The Pile)

Max Activating Token Index: 739

Text #8

Max Range: 3.2569. Min Range: -3.2569

Max Act: 3.0043. Min Act: -0.0000

Data Index: 1601930 (The Pile)

Max Activating Token Index: 378

Text #9

Max Range: 3.2569. Min Range: -3.2569

Max Act: 2.8926. Min Act: -0.0000

Data Index: 1442696 (The Pile)

Max Activating Token Index: 105

Text #10

Max Range: 3.2569. Min Range: -3.2569

Max Act: 2.8444. Min Act: -0.0000

Data Index: 623318 (The Pile)

Max Activating Token Index: 762

Text #11

Max Range: 3.2569. Min Range: -3.2569

Max Act: 2.7746. Min Act: -0.0000

Data Index: 455984 (The Pile)

Max Activating Token Index: 758

Text #12

Max Range: 3.2569. Min Range: -3.2569

Max Act: 2.9087. Min Act: -0.0000

Data Index: 556323 (The Pile)

Max Activating Token Index: 372

Text #13

Max Range: 3.2569. Min Range: -3.2569

Max Act: 2.9260. Min Act: -0.0000

Data Index: 1395820 (The Pile)

Max Activating Token Index: 635

Text #14

Max Range: 3.2569. Min Range: -3.2569

Max Act: 2.6133. Min Act: -0.0000

Data Index: 1584832 (The Pile)

Max Activating Token Index: 91

Text #15

Max Range: 3.2569. Min Range: -3.2569

Max Act: 2.6181. Min Act: -0.0000

Data Index: 24249 (The Pile)

Max Activating Token Index: 939

Text #16

Max Range: 3.2569. Min Range: -3.2569

Max Act: 2.7279. Min Act: -0.0000

Data Index: 391050 (The Pile)

Max Activating Token Index: 572

Text #17

Max Range: 3.2569. Min Range: -3.2569

Max Act: 2.8374. Min Act: -0.0000

Data Index: 620663 (The Pile)

Max Activating Token Index: 44

Text #18

Max Range: 3.2569. Min Range: -3.2569

Max Act: 2.6801. Min Act: -0.0000

Data Index: 769091 (The Pile)

Max Activating Token Index: 877

Text #19

Max Range: 3.2569. Min Range: -3.2569

Max Act: 2.5841. Min Act: -0.0000

Data Index: 845959 (The Pile)

Max Activating Token Index: 616