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

Dataset: The Pile

Neuron 1627 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3015. Min Range: -1.3015

Max Act: 1.3015. Min Act: -0.0000

Data Index: 235669 (The Pile)

Max Activating Token Index: 173

Text #1

Max Range: 1.3015. Min Range: -1.3015

Max Act: 1.2241. Min Act: -0.0000

Data Index: 1038100 (The Pile)

Max Activating Token Index: 562

Text #2

Max Range: 1.3015. Min Range: -1.3015

Max Act: 1.0916. Min Act: -0.0000

Data Index: 1977233 (The Pile)

Max Activating Token Index: 59

Text #3

Max Range: 1.3015. Min Range: -1.3015

Max Act: 1.2047. Min Act: -0.0000

Data Index: 794137 (The Pile)

Max Activating Token Index: 112

Text #4

Max Range: 1.3015. Min Range: -1.3015

Max Act: 1.1339. Min Act: -0.0000

Data Index: 748396 (The Pile)

Max Activating Token Index: 311

Text #5

Max Range: 1.3015. Min Range: -1.3015

Max Act: 1.1957. Min Act: -0.0000

Data Index: 230038 (The Pile)

Max Activating Token Index: 682

Text #6

Max Range: 1.3015. Min Range: -1.3015

Max Act: 1.0437. Min Act: -0.0000

Data Index: 1910948 (The Pile)

Max Activating Token Index: 341

Text #7

Max Range: 1.3015. Min Range: -1.3015

Max Act: 1.1055. Min Act: -0.0000

Data Index: 1432768 (The Pile)

Max Activating Token Index: 476

Text #8

Max Range: 1.3015. Min Range: -1.3015

Max Act: 0.8952. Min Act: -0.0000

Data Index: 767714 (The Pile)

Max Activating Token Index: 889

Text #9

Max Range: 1.3015. Min Range: -1.3015

Max Act: 1.0679. Min Act: -0.0000

Data Index: 678113 (The Pile)

Max Activating Token Index: 752

Text #10

Max Range: 1.3015. Min Range: -1.3015

Max Act: 0.9738. Min Act: -0.0000

Data Index: 1965256 (The Pile)

Max Activating Token Index: 90

Text #11

Max Range: 1.3015. Min Range: -1.3015

Max Act: 1.0150. Min Act: -0.0000

Data Index: 751256 (The Pile)

Max Activating Token Index: 295

Text #12

Max Range: 1.3015. Min Range: -1.3015

Max Act: 1.0686. Min Act: -0.0000

Data Index: 1047691 (The Pile)

Max Activating Token Index: 201

Text #13

Max Range: 1.3015. Min Range: -1.3015

Max Act: 0.9621. Min Act: -0.0000

Data Index: 1851979 (The Pile)

Max Activating Token Index: 476

Text #14

Max Range: 1.3015. Min Range: -1.3015

Max Act: 1.0494. Min Act: -0.0000

Data Index: 149104 (The Pile)

Max Activating Token Index: 8

Text #15

Max Range: 1.3015. Min Range: -1.3015

Max Act: 1.0516. Min Act: -0.0000

Data Index: 1992676 (The Pile)

Max Activating Token Index: 702

Text #16

Max Range: 1.3015. Min Range: -1.3015

Max Act: 1.0064. Min Act: -0.0000

Data Index: 532017 (The Pile)

Max Activating Token Index: 685

Text #17

Max Range: 1.3015. Min Range: -1.3015

Max Act: 0.9660. Min Act: -0.0000

Data Index: 1797242 (The Pile)

Max Activating Token Index: 891

Text #18

Max Range: 1.3015. Min Range: -1.3015

Max Act: 0.9655. Min Act: -0.0000

Data Index: 1800607 (The Pile)

Max Activating Token Index: 992

Text #19

Max Range: 1.3015. Min Range: -1.3015

Max Act: 0.9330. Min Act: -0.0000

Data Index: 129665 (The Pile)

Max Activating Token Index: 739