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

Dataset: The Pile

Neuron 3863 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: 0.8798. Min Range: -0.8798

Max Act: 0.8798. Min Act: -0.0000

Data Index: 731073 (The Pile)

Max Activating Token Index: 978

Text #1

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.6958. Min Act: -0.0000

Data Index: 1345423 (The Pile)

Max Activating Token Index: 431

Text #2

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.6946. Min Act: -0.0000

Data Index: 1637452 (The Pile)

Max Activating Token Index: 724

Text #3

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.6845. Min Act: -0.0000

Data Index: 940710 (The Pile)

Max Activating Token Index: 611

Text #4

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.6091. Min Act: -0.0000

Data Index: 1041878 (The Pile)

Max Activating Token Index: 106

Text #5

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.6249. Min Act: -0.0000

Data Index: 1261797 (The Pile)

Max Activating Token Index: 233

Text #6

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.6123. Min Act: -0.0000

Data Index: 1684909 (The Pile)

Max Activating Token Index: 700

Text #7

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.6535. Min Act: -0.0000

Data Index: 1613959 (The Pile)

Max Activating Token Index: 553

Text #8

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.5822. Min Act: -0.0000

Data Index: 114014 (The Pile)

Max Activating Token Index: 320

Text #9

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.5629. Min Act: -0.0000

Data Index: 1777387 (The Pile)

Max Activating Token Index: 383

Text #10

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.5888. Min Act: -0.0000

Data Index: 1624781 (The Pile)

Max Activating Token Index: 710

Text #11

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.4539. Min Act: -0.0000

Data Index: 1504743 (The Pile)

Max Activating Token Index: 739

Text #12

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.4951. Min Act: -0.0000

Data Index: 971626 (The Pile)

Max Activating Token Index: 970

Text #13

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.5743. Min Act: -0.0000

Data Index: 139886 (The Pile)

Max Activating Token Index: 236

Text #14

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.5085. Min Act: -0.0000

Data Index: 943076 (The Pile)

Max Activating Token Index: 942

Text #15

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.5226. Min Act: -0.0000

Data Index: 1158562 (The Pile)

Max Activating Token Index: 654

Text #16

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.4867. Min Act: -0.0000

Data Index: 1441016 (The Pile)

Max Activating Token Index: 809

Text #17

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.5083. Min Act: -0.0000

Data Index: 1745487 (The Pile)

Max Activating Token Index: 508

Text #18

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.4929. Min Act: -0.0000

Data Index: 1315637 (The Pile)

Max Activating Token Index: 723

Text #19

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.4975. Min Act: -0.0000

Data Index: 1891673 (The Pile)

Max Activating Token Index: 584