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

Dataset: The Pile

Neuron 1505 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: 0.7053. Min Range: -0.7053

Max Act: 0.6688. Min Act: -0.0000

Data Index: 457104 (The Pile)

Max Activating Token Index: 340

Text #1

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.7013. Min Act: -0.0000

Data Index: 729790 (The Pile)

Max Activating Token Index: 641

Text #2

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.6780. Min Act: -0.0000

Data Index: 1800293 (The Pile)

Max Activating Token Index: 783

Text #3

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.6711. Min Act: -0.0000

Data Index: 1399283 (The Pile)

Max Activating Token Index: 790

Text #4

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.6183. Min Act: -0.0000

Data Index: 364970 (The Pile)

Max Activating Token Index: 137

Text #5

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.6277. Min Act: -0.0000

Data Index: 1035775 (The Pile)

Max Activating Token Index: 623

Text #6

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.5989. Min Act: -0.0000

Data Index: 248236 (The Pile)

Max Activating Token Index: 937

Text #7

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.6700. Min Act: -0.0000

Data Index: 1801865 (The Pile)

Max Activating Token Index: 645

Text #8

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.6798. Min Act: -0.0000

Data Index: 1932873 (The Pile)

Max Activating Token Index: 245

Text #9

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.5648. Min Act: -0.0000

Data Index: 840068 (The Pile)

Max Activating Token Index: 562

Text #10

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.6060. Min Act: -0.0000

Data Index: 264297 (The Pile)

Max Activating Token Index: 793

Text #11

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.6028. Min Act: -0.0000

Data Index: 750297 (The Pile)

Max Activating Token Index: 963

Text #12

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.7053. Min Act: -0.0000

Data Index: 1660032 (The Pile)

Max Activating Token Index: 180

Text #13

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.6192. Min Act: -0.0000

Data Index: 1701165 (The Pile)

Max Activating Token Index: 159

Text #14

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.6016. Min Act: -0.0000

Data Index: 1693837 (The Pile)

Max Activating Token Index: 674

Text #15

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.6059. Min Act: -0.0000

Data Index: 516296 (The Pile)

Max Activating Token Index: 1002

Text #16

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.5879. Min Act: -0.0000

Data Index: 1720860 (The Pile)

Max Activating Token Index: 769

Text #17

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.5581. Min Act: -0.0000

Data Index: 1512084 (The Pile)

Max Activating Token Index: 1001

Text #18

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.5692. Min Act: -0.0000

Data Index: 705572 (The Pile)

Max Activating Token Index: 106

Text #19

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.5999. Min Act: -0.0000

Data Index: 1647009 (The Pile)

Max Activating Token Index: 630