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

Dataset: The Pile

Neuron 4500 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2793. Min Range: -1.2793

Max Act: 1.2793. Min Act: -0.0001

Data Index: 1897856 (The Pile)

Max Activating Token Index: 760

Text #1

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.9640. Min Act: -0.0000

Data Index: 1299284 (The Pile)

Max Activating Token Index: 395

Text #2

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.9222. Min Act: -0.0000

Data Index: 835642 (The Pile)

Max Activating Token Index: 831

Text #3

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.8032. Min Act: -0.0000

Data Index: 1278045 (The Pile)

Max Activating Token Index: 469

Text #4

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.9159. Min Act: -0.0000

Data Index: 1833449 (The Pile)

Max Activating Token Index: 576

Text #5

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.8777. Min Act: -0.0000

Data Index: 1053782 (The Pile)

Max Activating Token Index: 162

Text #6

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.8059. Min Act: -0.0000

Data Index: 1842597 (The Pile)

Max Activating Token Index: 875

Text #7

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.8002. Min Act: -0.0000

Data Index: 1462493 (The Pile)

Max Activating Token Index: 330

Text #8

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.8298. Min Act: -0.0000

Data Index: 619127 (The Pile)

Max Activating Token Index: 1009

Text #9

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.7821. Min Act: -0.0000

Data Index: 625580 (The Pile)

Max Activating Token Index: 146

Text #10

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.8070. Min Act: -0.0000

Data Index: 37722 (The Pile)

Max Activating Token Index: 781

Text #11

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.8336. Min Act: -0.0000

Data Index: 1220342 (The Pile)

Max Activating Token Index: 794

Text #12

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.7207. Min Act: -0.0000

Data Index: 1949560 (The Pile)

Max Activating Token Index: 805

Text #13

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.6779. Min Act: -0.0000

Data Index: 44445 (The Pile)

Max Activating Token Index: 193

Text #14

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.7354. Min Act: -0.0000

Data Index: 1855076 (The Pile)

Max Activating Token Index: 577

Text #15

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.7093. Min Act: -0.0000

Data Index: 1107304 (The Pile)

Max Activating Token Index: 508

Text #16

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.7345. Min Act: -0.0000

Data Index: 264856 (The Pile)

Max Activating Token Index: 751

Text #17

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.7022. Min Act: -0.0000

Data Index: 846170 (The Pile)

Max Activating Token Index: 867

Text #18

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.8009. Min Act: -0.0000

Data Index: 1019766 (The Pile)

Max Activating Token Index: 230

Text #19

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.6979. Min Act: -0.0000

Data Index: 746697 (The Pile)

Max Activating Token Index: 913