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

Dataset: The Pile

Neuron 2661 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.6029. Min Act: -0.0000

Data Index: 1466186 (The Pile)

Max Activating Token Index: 114

Text #1

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.3719. Min Act: -0.0000

Data Index: 1142498 (The Pile)

Max Activating Token Index: 798

Text #2

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.4047. Min Act: -0.0000

Data Index: 25626 (The Pile)

Max Activating Token Index: 425

Text #3

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.2373. Min Act: -0.0000

Data Index: 582057 (The Pile)

Max Activating Token Index: 532

Text #4

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.2914. Min Act: -0.0000

Data Index: 1533439 (The Pile)

Max Activating Token Index: 446

Text #5

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.3928. Min Act: -0.0000

Data Index: 1947358 (The Pile)

Max Activating Token Index: 85

Text #6

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.1306. Min Act: -0.0000

Data Index: 934731 (The Pile)

Max Activating Token Index: 125

Text #7

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.1065. Min Act: -0.0000

Data Index: 358935 (The Pile)

Max Activating Token Index: 635

Text #8

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.2340. Min Act: -0.0000

Data Index: 708508 (The Pile)

Max Activating Token Index: 887

Text #9

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.0522. Min Act: -0.0000

Data Index: 247230 (The Pile)

Max Activating Token Index: 931

Text #10

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.2037. Min Act: -0.0000

Data Index: 789533 (The Pile)

Max Activating Token Index: 198

Text #11

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.2794. Min Act: -0.0000

Data Index: 924879 (The Pile)

Max Activating Token Index: 35

Text #12

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.2029. Min Act: -0.0000

Data Index: 1565463 (The Pile)

Max Activating Token Index: 256

Text #13

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.0382. Min Act: -0.0000

Data Index: 792587 (The Pile)

Max Activating Token Index: 836

Text #14

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.1935. Min Act: -0.0000

Data Index: 1013693 (The Pile)

Max Activating Token Index: 952

Text #15

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.1558. Min Act: -0.0000

Data Index: 1002753 (The Pile)

Max Activating Token Index: 16

Text #16

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.0893. Min Act: -0.0000

Data Index: 1600417 (The Pile)

Max Activating Token Index: 381

Text #17

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.1066. Min Act: -0.0000

Data Index: 1573833 (The Pile)

Max Activating Token Index: 89

Text #18

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.0272. Min Act: -0.0000

Data Index: 1445581 (The Pile)

Max Activating Token Index: 149

Text #19

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.0892. Min Act: -0.0000

Data Index: 193327 (The Pile)

Max Activating Token Index: 629