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

Dataset: The Pile

Neuron 3224 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: 3.3529. Min Range: -3.3529

Max Act: 3.3529. Min Act: -0.0000

Data Index: 1713827 (The Pile)

Max Activating Token Index: 909

Text #1

Max Range: 3.3529. Min Range: -3.3529

Max Act: 2.2017. Min Act: -0.0000

Data Index: 902680 (The Pile)

Max Activating Token Index: 526

Text #2

Max Range: 3.3529. Min Range: -3.3529

Max Act: 1.8709. Min Act: -0.0000

Data Index: 905755 (The Pile)

Max Activating Token Index: 749

Text #3

Max Range: 3.3529. Min Range: -3.3529

Max Act: 1.8260. Min Act: 0.0000

Data Index: 403235 (The Pile)

Max Activating Token Index: 5

Text #4

Max Range: 3.3529. Min Range: -3.3529

Max Act: 1.4569. Min Act: -0.0000

Data Index: 724320 (The Pile)

Max Activating Token Index: 56

Text #5

Max Range: 3.3529. Min Range: -3.3529

Max Act: 1.2047. Min Act: -0.0000

Data Index: 186930 (The Pile)

Max Activating Token Index: 451

Text #6

Max Range: 3.3529. Min Range: -3.3529

Max Act: 1.1245. Min Act: -0.0000

Data Index: 1824519 (The Pile)

Max Activating Token Index: 709

Text #7

Max Range: 3.3529. Min Range: -3.3529

Max Act: 1.1937. Min Act: -0.0000

Data Index: 660879 (The Pile)

Max Activating Token Index: 956

Text #8

Max Range: 3.3529. Min Range: -3.3529

Max Act: 1.0935. Min Act: -0.0000

Data Index: 354049 (The Pile)

Max Activating Token Index: 625

Text #9

Max Range: 3.3529. Min Range: -3.3529

Max Act: 1.0985. Min Act: -0.0000

Data Index: 1204216 (The Pile)

Max Activating Token Index: 725

Text #10

Max Range: 3.3529. Min Range: -3.3529

Max Act: 1.0974. Min Act: -0.0000

Data Index: 110897 (The Pile)

Max Activating Token Index: 745

Text #11

Max Range: 3.3529. Min Range: -3.3529

Max Act: 1.0924. Min Act: -0.0000

Data Index: 548339 (The Pile)

Max Activating Token Index: 571

Text #12

Max Range: 3.3529. Min Range: -3.3529

Max Act: 1.0006. Min Act: -0.0000

Data Index: 1974380 (The Pile)

Max Activating Token Index: 667

Text #13

Max Range: 3.3529. Min Range: -3.3529

Max Act: 0.9845. Min Act: -0.0000

Data Index: 205273 (The Pile)

Max Activating Token Index: 1019

Text #14

Max Range: 3.3529. Min Range: -3.3529

Max Act: 0.9131. Min Act: -0.0000

Data Index: 1594048 (The Pile)

Max Activating Token Index: 266

Text #15

Max Range: 3.3529. Min Range: -3.3529

Max Act: 0.9865. Min Act: -0.0000

Data Index: 166324 (The Pile)

Max Activating Token Index: 521

Text #16

Max Range: 3.3529. Min Range: -3.3529

Max Act: 0.9067. Min Act: -0.0000

Data Index: 129128 (The Pile)

Max Activating Token Index: 632

Text #17

Max Range: 3.3529. Min Range: -3.3529

Max Act: 0.9012. Min Act: -0.0000

Data Index: 224058 (The Pile)

Max Activating Token Index: 542

Text #18

Max Range: 3.3529. Min Range: -3.3529

Max Act: 0.8981. Min Act: -0.0000

Data Index: 1045960 (The Pile)

Max Activating Token Index: 239

Text #19

Max Range: 3.3529. Min Range: -3.3529

Max Act: 0.8912. Min Act: -0.0000

Data Index: 966941 (The Pile)

Max Activating Token Index: 158