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

Dataset: The Pile

Neuron 2994 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: 1.0339. Min Range: -1.0339

Max Act: 1.0264. Min Act: -0.0000

Data Index: 1083845 (The Pile)

Max Activating Token Index: 111

Text #1

Max Range: 1.0339. Min Range: -1.0339

Max Act: 1.0121. Min Act: -0.0000

Data Index: 507028 (The Pile)

Max Activating Token Index: 165

Text #2

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.9521. Min Act: -0.0000

Data Index: 84324 (The Pile)

Max Activating Token Index: 247

Text #3

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.9569. Min Act: -0.0000

Data Index: 1519107 (The Pile)

Max Activating Token Index: 428

Text #4

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.9101. Min Act: -0.0000

Data Index: 28256 (The Pile)

Max Activating Token Index: 218

Text #5

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.9383. Min Act: -0.0000

Data Index: 1621953 (The Pile)

Max Activating Token Index: 975

Text #6

Max Range: 1.0339. Min Range: -1.0339

Max Act: 1.0339. Min Act: -0.0000

Data Index: 1386285 (The Pile)

Max Activating Token Index: 648

Text #7

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.8699. Min Act: -0.0000

Data Index: 1858031 (The Pile)

Max Activating Token Index: 183

Text #8

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.8414. Min Act: -0.0000

Data Index: 1313258 (The Pile)

Max Activating Token Index: 249

Text #9

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.8741. Min Act: -0.0000

Data Index: 1229214 (The Pile)

Max Activating Token Index: 391

Text #10

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.9528. Min Act: -0.0000

Data Index: 786037 (The Pile)

Max Activating Token Index: 288

Text #11

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.8902. Min Act: -0.0000

Data Index: 1431779 (The Pile)

Max Activating Token Index: 369

Text #12

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.8746. Min Act: -0.0000

Data Index: 1333342 (The Pile)

Max Activating Token Index: 624

Text #13

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.8265. Min Act: -0.0000

Data Index: 1292956 (The Pile)

Max Activating Token Index: 139

Text #14

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.8636. Min Act: -0.0000

Data Index: 866214 (The Pile)

Max Activating Token Index: 346

Text #15

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.8191. Min Act: -0.0000

Data Index: 1367672 (The Pile)

Max Activating Token Index: 111

Text #16

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.7772. Min Act: -0.0000

Data Index: 1494008 (The Pile)

Max Activating Token Index: 663

Text #17

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.7026. Min Act: -0.0000

Data Index: 1220016 (The Pile)

Max Activating Token Index: 859

Text #18

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.7397. Min Act: -0.0000

Data Index: 1896418 (The Pile)

Max Activating Token Index: 888

Text #19

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.8394. Min Act: -0.0000

Data Index: 588981 (The Pile)

Max Activating Token Index: 121