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

Dataset: The Pile

Neuron 2190 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: 1.6669. Min Range: -1.6669

Max Act: 1.6669. Min Act: -0.0000

Data Index: 1951904 (The Pile)

Max Activating Token Index: 266

Text #1

Max Range: 1.6669. Min Range: -1.6669

Max Act: 1.1797. Min Act: -0.0000

Data Index: 1115220 (The Pile)

Max Activating Token Index: 470

Text #2

Max Range: 1.6669. Min Range: -1.6669

Max Act: 1.2038. Min Act: -0.0000

Data Index: 1491771 (The Pile)

Max Activating Token Index: 624

Text #3

Max Range: 1.6669. Min Range: -1.6669

Max Act: 1.0664. Min Act: -0.0000

Data Index: 1240338 (The Pile)

Max Activating Token Index: 164

Text #4

Max Range: 1.6669. Min Range: -1.6669

Max Act: 0.8945. Min Act: -0.0000

Data Index: 653901 (The Pile)

Max Activating Token Index: 639

Text #5

Max Range: 1.6669. Min Range: -1.6669

Max Act: 0.9255. Min Act: -0.0000

Data Index: 234815 (The Pile)

Max Activating Token Index: 907

Text #6

Max Range: 1.6669. Min Range: -1.6669

Max Act: 0.7773. Min Act: -0.0000

Data Index: 971821 (The Pile)

Max Activating Token Index: 769

Text #7

Max Range: 1.6669. Min Range: -1.6669

Max Act: 0.7571. Min Act: -0.0000

Data Index: 1559868 (The Pile)

Max Activating Token Index: 314

Text #8

Max Range: 1.6669. Min Range: -1.6669

Max Act: 0.7295. Min Act: -0.0000

Data Index: 878605 (The Pile)

Max Activating Token Index: 524

Text #9

Max Range: 1.6669. Min Range: -1.6669

Max Act: 0.8548. Min Act: -0.0000

Data Index: 147313 (The Pile)

Max Activating Token Index: 665

Text #10

Max Range: 1.6669. Min Range: -1.6669

Max Act: 0.7257. Min Act: -0.0000

Data Index: 1182245 (The Pile)

Max Activating Token Index: 332

Text #11

Max Range: 1.6669. Min Range: -1.6669

Max Act: 0.7552. Min Act: -0.0000

Data Index: 878646 (The Pile)

Max Activating Token Index: 231

Text #12

Max Range: 1.6669. Min Range: -1.6669

Max Act: 0.7016. Min Act: 0.0001

Data Index: 1262286 (The Pile)

Max Activating Token Index: 739

Text #13

Max Range: 1.6669. Min Range: -1.6669

Max Act: 0.7012. Min Act: -0.0000

Data Index: 294561 (The Pile)

Max Activating Token Index: 578

Text #14

Max Range: 1.6669. Min Range: -1.6669

Max Act: 0.7426. Min Act: -0.0000

Data Index: 1962365 (The Pile)

Max Activating Token Index: 768

Text #15

Max Range: 1.6669. Min Range: -1.6669

Max Act: 0.6720. Min Act: -0.0000

Data Index: 1149971 (The Pile)

Max Activating Token Index: 292

Text #16

Max Range: 1.6669. Min Range: -1.6669

Max Act: 0.7247. Min Act: -0.0000

Data Index: 39745 (The Pile)

Max Activating Token Index: 760

Text #17

Max Range: 1.6669. Min Range: -1.6669

Max Act: 0.6698. Min Act: -0.0000

Data Index: 1121830 (The Pile)

Max Activating Token Index: 867

Text #18

Max Range: 1.6669. Min Range: -1.6669

Max Act: 0.6100. Min Act: -0.0000

Data Index: 1829761 (The Pile)

Max Activating Token Index: 290

Text #19

Max Range: 1.6669. Min Range: -1.6669

Max Act: 0.7118. Min Act: -0.0000

Data Index: 810027 (The Pile)

Max Activating Token Index: 189