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

Dataset: The Pile

Neuron 2748 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8221. Min Range: -1.8221

Max Act: 1.8221. Min Act: -0.0000

Data Index: 463946 (The Pile)

Max Activating Token Index: 906

Text #1

Max Range: 1.8221. Min Range: -1.8221

Max Act: 1.6828. Min Act: -0.0000

Data Index: 207890 (The Pile)

Max Activating Token Index: 486

Text #2

Max Range: 1.8221. Min Range: -1.8221

Max Act: 1.6173. Min Act: -0.0000

Data Index: 1899570 (The Pile)

Max Activating Token Index: 885

Text #3

Max Range: 1.8221. Min Range: -1.8221

Max Act: 1.4174. Min Act: -0.0000

Data Index: 1544829 (The Pile)

Max Activating Token Index: 1022

Text #4

Max Range: 1.8221. Min Range: -1.8221

Max Act: 1.4610. Min Act: -0.0000

Data Index: 1437780 (The Pile)

Max Activating Token Index: 698

Text #5

Max Range: 1.8221. Min Range: -1.8221

Max Act: 1.4881. Min Act: -0.0000

Data Index: 1377366 (The Pile)

Max Activating Token Index: 61

Text #6

Max Range: 1.8221. Min Range: -1.8221

Max Act: 1.3974. Min Act: -0.0000

Data Index: 26157 (The Pile)

Max Activating Token Index: 849

Text #7

Max Range: 1.8221. Min Range: -1.8221

Max Act: 1.4742. Min Act: -0.0000

Data Index: 459929 (The Pile)

Max Activating Token Index: 7

Text #8

Max Range: 1.8221. Min Range: -1.8221

Max Act: 1.3844. Min Act: -0.0000

Data Index: 1425530 (The Pile)

Max Activating Token Index: 290

Text #9

Max Range: 1.8221. Min Range: -1.8221

Max Act: 1.3885. Min Act: -0.0000

Data Index: 308805 (The Pile)

Max Activating Token Index: 49

Text #10

Max Range: 1.8221. Min Range: -1.8221

Max Act: 1.3840. Min Act: -0.0000

Data Index: 816757 (The Pile)

Max Activating Token Index: 228

Text #11

Max Range: 1.8221. Min Range: -1.8221

Max Act: 1.3758. Min Act: -0.0000

Data Index: 1803146 (The Pile)

Max Activating Token Index: 979

Text #12

Max Range: 1.8221. Min Range: -1.8221

Max Act: 1.3672. Min Act: -0.0000

Data Index: 1954831 (The Pile)

Max Activating Token Index: 186

Text #13

Max Range: 1.8221. Min Range: -1.8221

Max Act: 1.3552. Min Act: -0.0000

Data Index: 647906 (The Pile)

Max Activating Token Index: 199

Text #14

Max Range: 1.8221. Min Range: -1.8221

Max Act: 1.2664. Min Act: -0.0000

Data Index: 524685 (The Pile)

Max Activating Token Index: 303

Text #15

Max Range: 1.8221. Min Range: -1.8221

Max Act: 1.2544. Min Act: -0.0000

Data Index: 162132 (The Pile)

Max Activating Token Index: 27

Text #16

Max Range: 1.8221. Min Range: -1.8221

Max Act: 1.1699. Min Act: -0.0000

Data Index: 566541 (The Pile)

Max Activating Token Index: 762

Text #17

Max Range: 1.8221. Min Range: -1.8221

Max Act: 1.3805. Min Act: -0.0000

Data Index: 229424 (The Pile)

Max Activating Token Index: 421

Text #18

Max Range: 1.8221. Min Range: -1.8221

Max Act: 1.2995. Min Act: -0.0000

Data Index: 676400 (The Pile)

Max Activating Token Index: 210

Text #19

Max Range: 1.8221. Min Range: -1.8221

Max Act: 1.2781. Min Act: -0.0000

Data Index: 1158406 (The Pile)

Max Activating Token Index: 639