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

Dataset: The Pile

Neuron 865 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: 0.6936. Min Range: -0.6936

Max Act: 0.6936. Min Act: -0.0000

Data Index: 841044 (The Pile)

Max Activating Token Index: 450

Text #1

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5961. Min Act: -0.0000

Data Index: 402784 (The Pile)

Max Activating Token Index: 69

Text #2

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.6152. Min Act: -0.0000

Data Index: 1927566 (The Pile)

Max Activating Token Index: 1022

Text #3

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5718. Min Act: -0.0000

Data Index: 1413767 (The Pile)

Max Activating Token Index: 775

Text #4

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5764. Min Act: -0.0000

Data Index: 603490 (The Pile)

Max Activating Token Index: 152

Text #5

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5876. Min Act: -0.0000

Data Index: 634179 (The Pile)

Max Activating Token Index: 848

Text #6

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5561. Min Act: -0.0000

Data Index: 1338972 (The Pile)

Max Activating Token Index: 344

Text #7

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.6091. Min Act: -0.0000

Data Index: 1291137 (The Pile)

Max Activating Token Index: 370

Text #8

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5607. Min Act: -0.0000

Data Index: 231952 (The Pile)

Max Activating Token Index: 663

Text #9

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.4360. Min Act: -0.0000

Data Index: 45894 (The Pile)

Max Activating Token Index: 962

Text #10

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5596. Min Act: -0.0000

Data Index: 812251 (The Pile)

Max Activating Token Index: 48

Text #11

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5185. Min Act: -0.0000

Data Index: 116757 (The Pile)

Max Activating Token Index: 341

Text #12

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5257. Min Act: -0.0000

Data Index: 530316 (The Pile)

Max Activating Token Index: 62

Text #13

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5636. Min Act: -0.0000

Data Index: 1901489 (The Pile)

Max Activating Token Index: 867

Text #14

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5368. Min Act: -0.0000

Data Index: 951551 (The Pile)

Max Activating Token Index: 462

Text #15

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5161. Min Act: -0.0000

Data Index: 61836 (The Pile)

Max Activating Token Index: 582

Text #16

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5304. Min Act: -0.0000

Data Index: 1092516 (The Pile)

Max Activating Token Index: 512

Text #17

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.4849. Min Act: -0.0000

Data Index: 1427956 (The Pile)

Max Activating Token Index: 43

Text #18

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5020. Min Act: -0.0000

Data Index: 525940 (The Pile)

Max Activating Token Index: 364

Text #19

Max Range: 0.6936. Min Range: -0.6936

Max Act: 0.5150. Min Act: -0.0000

Data Index: 496114 (The Pile)

Max Activating Token Index: 384