Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2679 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 1.0258. Min Range: -1.0258

Max Act: 1.0258. Min Act: -0.0000

Data Index: 995319 (The Pile)

Max Activating Token Index: 601

Text #1

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.9827. Min Act: -0.0001

Data Index: 1693704 (The Pile)

Max Activating Token Index: 681

Text #2

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.8139. Min Act: -0.0000

Data Index: 223569 (The Pile)

Max Activating Token Index: 198

Text #3

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.8566. Min Act: -0.0001

Data Index: 122328 (The Pile)

Max Activating Token Index: 767

Text #4

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.7205. Min Act: -0.0000

Data Index: 27713 (The Pile)

Max Activating Token Index: 622

Text #5

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.7062. Min Act: -0.0000

Data Index: 1914935 (The Pile)

Max Activating Token Index: 416

Text #6

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.6957. Min Act: -0.0001

Data Index: 1061517 (The Pile)

Max Activating Token Index: 397

Text #7

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.6353. Min Act: -0.0000

Data Index: 456357 (The Pile)

Max Activating Token Index: 670

Text #8

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.6772. Min Act: -0.0000

Data Index: 475950 (The Pile)

Max Activating Token Index: 626

Text #9

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.6779. Min Act: -0.0000

Data Index: 1277570 (The Pile)

Max Activating Token Index: 529

Text #10

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.6550. Min Act: -0.0001

Data Index: 1704736 (The Pile)

Max Activating Token Index: 774

Text #11

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.6613. Min Act: -0.0001

Data Index: 727541 (The Pile)

Max Activating Token Index: 201

Text #12

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.6621. Min Act: -0.0000

Data Index: 673040 (The Pile)

Max Activating Token Index: 815

Text #13

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.6122. Min Act: 0.0000

Data Index: 45691 (The Pile)

Max Activating Token Index: 691

Text #14

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.6535. Min Act: -0.0000

Data Index: 1995695 (The Pile)

Max Activating Token Index: 518

Text #15

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.6289. Min Act: -0.0000

Data Index: 296933 (The Pile)

Max Activating Token Index: 682

Text #16

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.5952. Min Act: -0.0000

Data Index: 1911121 (The Pile)

Max Activating Token Index: 630

Text #17

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.5951. Min Act: -0.0000

Data Index: 369424 (The Pile)

Max Activating Token Index: 219

Text #18

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.6275. Min Act: -0.0001

Data Index: 60562 (The Pile)

Max Activating Token Index: 969

Text #19

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.5757. Min Act: -0.0000

Data Index: 1901968 (The Pile)

Max Activating Token Index: 1018