Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: The Pile

Neuron 766 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l-pile')

Text #0

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.6583. Min Act: -0.0001

Data Index: 159285 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.6909. Min Act: -0.0000

Data Index: 1155809 (The Pile)

Max Activating Token Index: 985

Text #2

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.6801. Min Act: -0.0000

Data Index: 1550648 (The Pile)

Max Activating Token Index: 93

Text #3

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.6248. Min Act: -0.0001

Data Index: 695484 (The Pile)

Max Activating Token Index: 851

Text #4

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.5951. Min Act: -0.0000

Data Index: 493096 (The Pile)

Max Activating Token Index: 580

Text #5

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.5987. Min Act: -0.0000

Data Index: 1393364 (The Pile)

Max Activating Token Index: 226

Text #6

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.6320. Min Act: -0.0000

Data Index: 721759 (The Pile)

Max Activating Token Index: 384

Text #7

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.6100. Min Act: -0.0000

Data Index: 865317 (The Pile)

Max Activating Token Index: 501

Text #8

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.6421. Min Act: -0.0000

Data Index: 711231 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.5961. Min Act: -0.0001

Data Index: 1550807 (The Pile)

Max Activating Token Index: 837

Text #10

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.5764. Min Act: -0.0000

Data Index: 135433 (The Pile)

Max Activating Token Index: 652

Text #11

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.5978. Min Act: -0.0000

Data Index: 435965 (The Pile)

Max Activating Token Index: 822

Text #12

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.5756. Min Act: -0.0000

Data Index: 1527842 (The Pile)

Max Activating Token Index: 65

Text #13

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.5892. Min Act: -0.0000

Data Index: 1693275 (The Pile)

Max Activating Token Index: 253

Text #14

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.5706. Min Act: -0.0001

Data Index: 768392 (The Pile)

Max Activating Token Index: 998

Text #15

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.5679. Min Act: -0.0000

Data Index: 1637266 (The Pile)

Max Activating Token Index: 772

Text #16

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.5496. Min Act: -0.0000

Data Index: 993108 (The Pile)

Max Activating Token Index: 345

Text #17

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.5570. Min Act: -0.0001

Data Index: 1876468 (The Pile)

Max Activating Token Index: 695

Text #18

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.5382. Min Act: -0.0001

Data Index: 236828 (The Pile)

Max Activating Token Index: 965

Text #19

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.5226. Min Act: -0.0000

Data Index: 954207 (The Pile)

Max Activating Token Index: 697