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

Dataset: The Pile

Neuron 3758 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: 4.3598. Min Range: -4.3598

Max Act: 4.3598. Min Act: -0.0000

Data Index: 750469 (The Pile)

Max Activating Token Index: 500

Text #1

Max Range: 4.3598. Min Range: -4.3598

Max Act: 3.8931. Min Act: -0.0000

Data Index: 208101 (The Pile)

Max Activating Token Index: 769

Text #2

Max Range: 4.3598. Min Range: -4.3598

Max Act: 3.6952. Min Act: -0.0000

Data Index: 976397 (The Pile)

Max Activating Token Index: 855

Text #3

Max Range: 4.3598. Min Range: -4.3598

Max Act: 3.6701. Min Act: -0.0000

Data Index: 760599 (The Pile)

Max Activating Token Index: 721

Text #4

Max Range: 4.3598. Min Range: -4.3598

Max Act: 3.7425. Min Act: -0.0000

Data Index: 1905500 (The Pile)

Max Activating Token Index: 621

Text #5

Max Range: 4.3598. Min Range: -4.3598

Max Act: 4.2098. Min Act: -0.0000

Data Index: 435277 (The Pile)

Max Activating Token Index: 567

Text #6

Max Range: 4.3598. Min Range: -4.3598

Max Act: 3.5585. Min Act: -0.0000

Data Index: 1077447 (The Pile)

Max Activating Token Index: 673

Text #7

Max Range: 4.3598. Min Range: -4.3598

Max Act: 3.6618. Min Act: -0.0000

Data Index: 1116172 (The Pile)

Max Activating Token Index: 732

Text #8

Max Range: 4.3598. Min Range: -4.3598

Max Act: 3.6336. Min Act: -0.0000

Data Index: 1056789 (The Pile)

Max Activating Token Index: 802

Text #9

Max Range: 4.3598. Min Range: -4.3598

Max Act: 3.4621. Min Act: -0.0000

Data Index: 1924977 (The Pile)

Max Activating Token Index: 847

Text #10

Max Range: 4.3598. Min Range: -4.3598

Max Act: 3.3111. Min Act: -0.0000

Data Index: 1971850 (The Pile)

Max Activating Token Index: 610

Text #11

Max Range: 4.3598. Min Range: -4.3598

Max Act: 3.3813. Min Act: -0.0000

Data Index: 407327 (The Pile)

Max Activating Token Index: 503

Text #12

Max Range: 4.3598. Min Range: -4.3598

Max Act: 3.6581. Min Act: -0.0000

Data Index: 1537556 (The Pile)

Max Activating Token Index: 513

Text #13

Max Range: 4.3598. Min Range: -4.3598

Max Act: 3.5519. Min Act: -0.0000

Data Index: 717028 (The Pile)

Max Activating Token Index: 659

Text #14

Max Range: 4.3598. Min Range: -4.3598

Max Act: 3.4245. Min Act: -0.0000

Data Index: 1639125 (The Pile)

Max Activating Token Index: 560

Text #15

Max Range: 4.3598. Min Range: -4.3598

Max Act: 3.3985. Min Act: -0.0000

Data Index: 1974700 (The Pile)

Max Activating Token Index: 894

Text #16

Max Range: 4.3598. Min Range: -4.3598

Max Act: 3.5494. Min Act: -0.0000

Data Index: 297640 (The Pile)

Max Activating Token Index: 993

Text #17

Max Range: 4.3598. Min Range: -4.3598

Max Act: 3.5686. Min Act: -0.0000

Data Index: 1721292 (The Pile)

Max Activating Token Index: 603

Text #18

Max Range: 4.3598. Min Range: -4.3598

Max Act: 3.3489. Min Act: -0.0000

Data Index: 624775 (The Pile)

Max Activating Token Index: 551

Text #19

Max Range: 4.3598. Min Range: -4.3598

Max Act: 3.6729. Min Act: -0.0000

Data Index: 1615229 (The Pile)

Max Activating Token Index: 786