Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1408 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1846. Min Range: -1.1846

Max Act: 1.1547. Min Act: -0.0000

Data Index: 1113418 (The Pile)

Max Activating Token Index: 666

Text #1

Max Range: 1.1846. Min Range: -1.1846

Max Act: 1.1846. Min Act: -0.0000

Data Index: 586442 (The Pile)

Max Activating Token Index: 726

Text #2

Max Range: 1.1846. Min Range: -1.1846

Max Act: 1.0553. Min Act: -0.0000

Data Index: 1693564 (The Pile)

Max Activating Token Index: 753

Text #3

Max Range: 1.1846. Min Range: -1.1846

Max Act: 0.9634. Min Act: -0.0000

Data Index: 1972164 (The Pile)

Max Activating Token Index: 513

Text #4

Max Range: 1.1846. Min Range: -1.1846

Max Act: 1.1089. Min Act: -0.0000

Data Index: 1828972 (The Pile)

Max Activating Token Index: 991

Text #5

Max Range: 1.1846. Min Range: -1.1846

Max Act: 1.0913. Min Act: -0.0000

Data Index: 859924 (The Pile)

Max Activating Token Index: 920

Text #6

Max Range: 1.1846. Min Range: -1.1846

Max Act: 0.9890. Min Act: -0.0000

Data Index: 895969 (The Pile)

Max Activating Token Index: 724

Text #7

Max Range: 1.1846. Min Range: -1.1846

Max Act: 1.0475. Min Act: -0.0000

Data Index: 607118 (The Pile)

Max Activating Token Index: 586

Text #8

Max Range: 1.1846. Min Range: -1.1846

Max Act: 0.9844. Min Act: -0.0000

Data Index: 463954 (The Pile)

Max Activating Token Index: 684

Text #9

Max Range: 1.1846. Min Range: -1.1846

Max Act: 0.9837. Min Act: -0.0000

Data Index: 332291 (The Pile)

Max Activating Token Index: 497

Text #10

Max Range: 1.1846. Min Range: -1.1846

Max Act: 0.9489. Min Act: -0.0000

Data Index: 860647 (The Pile)

Max Activating Token Index: 32

Text #11

Max Range: 1.1846. Min Range: -1.1846

Max Act: 1.0826. Min Act: -0.0000

Data Index: 89372 (The Pile)

Max Activating Token Index: 678

Text #12

Max Range: 1.1846. Min Range: -1.1846

Max Act: 0.9495. Min Act: -0.0000

Data Index: 557865 (The Pile)

Max Activating Token Index: 92

Text #13

Max Range: 1.1846. Min Range: -1.1846

Max Act: 1.0079. Min Act: -0.0000

Data Index: 1655219 (The Pile)

Max Activating Token Index: 294

Text #14

Max Range: 1.1846. Min Range: -1.1846

Max Act: 1.0803. Min Act: -0.0000

Data Index: 1276012 (The Pile)

Max Activating Token Index: 503

Text #15

Max Range: 1.1846. Min Range: -1.1846

Max Act: 0.9734. Min Act: -0.0000

Data Index: 1626006 (The Pile)

Max Activating Token Index: 601

Text #16

Max Range: 1.1846. Min Range: -1.1846

Max Act: 0.8772. Min Act: -0.0000

Data Index: 1180501 (The Pile)

Max Activating Token Index: 666

Text #17

Max Range: 1.1846. Min Range: -1.1846

Max Act: 1.0075. Min Act: -0.0000

Data Index: 605119 (The Pile)

Max Activating Token Index: 729

Text #18

Max Range: 1.1846. Min Range: -1.1846

Max Act: 1.0423. Min Act: -0.0000

Data Index: 1535172 (The Pile)

Max Activating Token Index: 108

Text #19

Max Range: 1.1846. Min Range: -1.1846

Max Act: 1.0247. Min Act: -0.0000

Data Index: 730030 (The Pile)

Max Activating Token Index: 142