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

Dataset: The Pile

Neuron 3577 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: 1.5985. Min Range: -1.5985

Max Act: 1.5985. Min Act: -0.0000

Data Index: 1732393 (The Pile)

Max Activating Token Index: 402

Text #1

Max Range: 1.5985. Min Range: -1.5985

Max Act: 1.3669. Min Act: -0.0000

Data Index: 907486 (The Pile)

Max Activating Token Index: 186

Text #2

Max Range: 1.5985. Min Range: -1.5985

Max Act: 1.2285. Min Act: -0.0000

Data Index: 794922 (The Pile)

Max Activating Token Index: 369

Text #3

Max Range: 1.5985. Min Range: -1.5985

Max Act: 1.3211. Min Act: -0.0000

Data Index: 291513 (The Pile)

Max Activating Token Index: 581

Text #4

Max Range: 1.5985. Min Range: -1.5985

Max Act: 1.2316. Min Act: 0.0000

Data Index: 634551 (The Pile)

Max Activating Token Index: 593

Text #5

Max Range: 1.5985. Min Range: -1.5985

Max Act: 1.1783. Min Act: -0.0000

Data Index: 1150774 (The Pile)

Max Activating Token Index: 436

Text #6

Max Range: 1.5985. Min Range: -1.5985

Max Act: 1.1425. Min Act: -0.0000

Data Index: 1191584 (The Pile)

Max Activating Token Index: 242

Text #7

Max Range: 1.5985. Min Range: -1.5985

Max Act: 1.0774. Min Act: -0.0000

Data Index: 859986 (The Pile)

Max Activating Token Index: 817

Text #8

Max Range: 1.5985. Min Range: -1.5985

Max Act: 1.0216. Min Act: -0.0000

Data Index: 939029 (The Pile)

Max Activating Token Index: 215

Text #9

Max Range: 1.5985. Min Range: -1.5985

Max Act: 1.0621. Min Act: -0.0000

Data Index: 1773432 (The Pile)

Max Activating Token Index: 173

Text #10

Max Range: 1.5985. Min Range: -1.5985

Max Act: 1.0656. Min Act: -0.0000

Data Index: 707611 (The Pile)

Max Activating Token Index: 136

Text #11

Max Range: 1.5985. Min Range: -1.5985

Max Act: 0.9840. Min Act: -0.0000

Data Index: 254051 (The Pile)

Max Activating Token Index: 70

Text #12

Max Range: 1.5985. Min Range: -1.5985

Max Act: 1.0167. Min Act: 0.0000

Data Index: 1189821 (The Pile)

Max Activating Token Index: 166

Text #13

Max Range: 1.5985. Min Range: -1.5985

Max Act: 0.9578. Min Act: -0.0000

Data Index: 265588 (The Pile)

Max Activating Token Index: 973

Text #14

Max Range: 1.5985. Min Range: -1.5985

Max Act: 1.0698. Min Act: -0.0000

Data Index: 235946 (The Pile)

Max Activating Token Index: 657

Text #15

Max Range: 1.5985. Min Range: -1.5985

Max Act: 0.9936. Min Act: -0.0000

Data Index: 255802 (The Pile)

Max Activating Token Index: 197

Text #16

Max Range: 1.5985. Min Range: -1.5985

Max Act: 0.9888. Min Act: -0.0000

Data Index: 1316551 (The Pile)

Max Activating Token Index: 909

Text #17

Max Range: 1.5985. Min Range: -1.5985

Max Act: 0.9283. Min Act: -0.0000

Data Index: 806961 (The Pile)

Max Activating Token Index: 183

Text #18

Max Range: 1.5985. Min Range: -1.5985

Max Act: 0.9282. Min Act: -0.0000

Data Index: 1631293 (The Pile)

Max Activating Token Index: 232

Text #19

Max Range: 1.5985. Min Range: -1.5985

Max Act: 0.9933. Min Act: -0.0000

Data Index: 302265 (The Pile)

Max Activating Token Index: 685