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

Dataset: The Pile

Neuron 4718 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: 0.7068. Min Range: -0.7068

Max Act: 0.6958. Min Act: -0.0000

Data Index: 834324 (The Pile)

Max Activating Token Index: 171

Text #1

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.7068. Min Act: -0.0000

Data Index: 694369 (The Pile)

Max Activating Token Index: 179

Text #2

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.7065. Min Act: -0.0000

Data Index: 344391 (The Pile)

Max Activating Token Index: 639

Text #3

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.6434. Min Act: -0.0000

Data Index: 860472 (The Pile)

Max Activating Token Index: 369

Text #4

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.6046. Min Act: -0.0000

Data Index: 407889 (The Pile)

Max Activating Token Index: 848

Text #5

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.6527. Min Act: -0.0000

Data Index: 1079676 (The Pile)

Max Activating Token Index: 59

Text #6

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.5925. Min Act: -0.0000

Data Index: 1140819 (The Pile)

Max Activating Token Index: 448

Text #7

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.6196. Min Act: -0.0000

Data Index: 1446925 (The Pile)

Max Activating Token Index: 703

Text #8

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.5930. Min Act: -0.0000

Data Index: 587257 (The Pile)

Max Activating Token Index: 488

Text #9

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.5517. Min Act: -0.0000

Data Index: 1795611 (The Pile)

Max Activating Token Index: 172

Text #10

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.5724. Min Act: -0.0000

Data Index: 563471 (The Pile)

Max Activating Token Index: 310

Text #11

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.5192. Min Act: -0.0000

Data Index: 1679839 (The Pile)

Max Activating Token Index: 636

Text #12

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.5353. Min Act: -0.0000

Data Index: 477456 (The Pile)

Max Activating Token Index: 43

Text #13

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.5417. Min Act: -0.0000

Data Index: 898659 (The Pile)

Max Activating Token Index: 442

Text #14

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.5231. Min Act: -0.0000

Data Index: 1140682 (The Pile)

Max Activating Token Index: 313

Text #15

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.5088. Min Act: -0.0000

Data Index: 228749 (The Pile)

Max Activating Token Index: 230

Text #16

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.5327. Min Act: -0.0000

Data Index: 1934860 (The Pile)

Max Activating Token Index: 23

Text #17

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.5530. Min Act: -0.0000

Data Index: 1192936 (The Pile)

Max Activating Token Index: 289

Text #18

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.5448. Min Act: -0.0000

Data Index: 1760592 (The Pile)

Max Activating Token Index: 142

Text #19

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.5030. Min Act: -0.0000

Data Index: 1134611 (The Pile)

Max Activating Token Index: 37