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

Dataset: The Pile

Neuron 2147 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.7765. Min Act: -0.0000

Data Index: 1080882 (The Pile)

Max Activating Token Index: 166

Text #1

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.7222. Min Act: -0.0000

Data Index: 493332 (The Pile)

Max Activating Token Index: 29

Text #2

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.6898. Min Act: -0.0000

Data Index: 335112 (The Pile)

Max Activating Token Index: 106

Text #3

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.7272. Min Act: -0.0000

Data Index: 1649736 (The Pile)

Max Activating Token Index: 57

Text #4

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.7142. Min Act: -0.0000

Data Index: 1066856 (The Pile)

Max Activating Token Index: 916

Text #5

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.6923. Min Act: -0.0000

Data Index: 1847642 (The Pile)

Max Activating Token Index: 242

Text #6

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.6807. Min Act: -0.0000

Data Index: 953673 (The Pile)

Max Activating Token Index: 275

Text #7

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.6165. Min Act: -0.0000

Data Index: 1818595 (The Pile)

Max Activating Token Index: 373

Text #8

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.6542. Min Act: -0.0000

Data Index: 1000960 (The Pile)

Max Activating Token Index: 597

Text #9

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.6258. Min Act: -0.0000

Data Index: 597948 (The Pile)

Max Activating Token Index: 272

Text #10

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.5979. Min Act: -0.0000

Data Index: 201057 (The Pile)

Max Activating Token Index: 246

Text #11

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.6137. Min Act: -0.0000

Data Index: 1415868 (The Pile)

Max Activating Token Index: 555

Text #12

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.6046. Min Act: -0.0000

Data Index: 1432836 (The Pile)

Max Activating Token Index: 224

Text #13

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.6036. Min Act: -0.0000

Data Index: 399725 (The Pile)

Max Activating Token Index: 88

Text #14

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.5943. Min Act: -0.0000

Data Index: 462601 (The Pile)

Max Activating Token Index: 244

Text #15

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.5762. Min Act: -0.0000

Data Index: 695447 (The Pile)

Max Activating Token Index: 602

Text #16

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.5703. Min Act: -0.0000

Data Index: 894513 (The Pile)

Max Activating Token Index: 485

Text #17

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.5724. Min Act: -0.0001

Data Index: 1290897 (The Pile)

Max Activating Token Index: 146

Text #18

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.5848. Min Act: -0.0000

Data Index: 567609 (The Pile)

Max Activating Token Index: 446

Text #19

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.5749. Min Act: -0.0000

Data Index: 496280 (The Pile)

Max Activating Token Index: 742