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

Dataset: The Pile

Neuron 1697 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.5555. Min Range: -1.5555

Max Act: 1.5555. Min Act: -0.0000

Data Index: 1927384 (The Pile)

Max Activating Token Index: 505

Text #1

Max Range: 1.5555. Min Range: -1.5555

Max Act: 1.3048. Min Act: -0.0000

Data Index: 785952 (The Pile)

Max Activating Token Index: 491

Text #2

Max Range: 1.5555. Min Range: -1.5555

Max Act: 1.2099. Min Act: -0.0000

Data Index: 1058965 (The Pile)

Max Activating Token Index: 625

Text #3

Max Range: 1.5555. Min Range: -1.5555

Max Act: 1.1372. Min Act: -0.0000

Data Index: 1539421 (The Pile)

Max Activating Token Index: 119

Text #4

Max Range: 1.5555. Min Range: -1.5555

Max Act: 1.0625. Min Act: -0.0000

Data Index: 1514064 (The Pile)

Max Activating Token Index: 846

Text #5

Max Range: 1.5555. Min Range: -1.5555

Max Act: 1.1402. Min Act: -0.0000

Data Index: 1841621 (The Pile)

Max Activating Token Index: 384

Text #6

Max Range: 1.5555. Min Range: -1.5555

Max Act: 0.9714. Min Act: -0.0000

Data Index: 390863 (The Pile)

Max Activating Token Index: 948

Text #7

Max Range: 1.5555. Min Range: -1.5555

Max Act: 0.9673. Min Act: -0.0000

Data Index: 1582094 (The Pile)

Max Activating Token Index: 888

Text #8

Max Range: 1.5555. Min Range: -1.5555

Max Act: 1.0281. Min Act: -0.0000

Data Index: 1113474 (The Pile)

Max Activating Token Index: 145

Text #9

Max Range: 1.5555. Min Range: -1.5555

Max Act: 1.0552. Min Act: -0.0000

Data Index: 1397678 (The Pile)

Max Activating Token Index: 369

Text #10

Max Range: 1.5555. Min Range: -1.5555

Max Act: 1.1198. Min Act: -0.0000

Data Index: 1639940 (The Pile)

Max Activating Token Index: 712

Text #11

Max Range: 1.5555. Min Range: -1.5555

Max Act: 0.8593. Min Act: -0.0000

Data Index: 428883 (The Pile)

Max Activating Token Index: 730

Text #12

Max Range: 1.5555. Min Range: -1.5555

Max Act: 0.9843. Min Act: -0.0000

Data Index: 1409538 (The Pile)

Max Activating Token Index: 370

Text #13

Max Range: 1.5555. Min Range: -1.5555

Max Act: 0.8789. Min Act: -0.0000

Data Index: 1158478 (The Pile)

Max Activating Token Index: 175

Text #14

Max Range: 1.5555. Min Range: -1.5555

Max Act: 0.8926. Min Act: -0.0000

Data Index: 816488 (The Pile)

Max Activating Token Index: 541

Text #15

Max Range: 1.5555. Min Range: -1.5555

Max Act: 0.7012. Min Act: -0.0000

Data Index: 637173 (The Pile)

Max Activating Token Index: 829

Text #16

Max Range: 1.5555. Min Range: -1.5555

Max Act: 0.8842. Min Act: -0.0000

Data Index: 1979843 (The Pile)

Max Activating Token Index: 725

Text #17

Max Range: 1.5555. Min Range: -1.5555

Max Act: 0.8121. Min Act: -0.0000

Data Index: 1232571 (The Pile)

Max Activating Token Index: 904

Text #18

Max Range: 1.5555. Min Range: -1.5555

Max Act: 0.8143. Min Act: -0.0000

Data Index: 1769061 (The Pile)

Max Activating Token Index: 393

Text #19

Max Range: 1.5555. Min Range: -1.5555

Max Act: 0.8886. Min Act: -0.0000

Data Index: 800685 (The Pile)

Max Activating Token Index: 84