Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 613 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1258. Min Range: -1.1258

Max Act: 1.0588. Min Act: -0.0000

Data Index: 1255703 (The Pile)

Max Activating Token Index: 579

Text #1

Max Range: 1.1258. Min Range: -1.1258

Max Act: 1.1258. Min Act: 0.0000

Data Index: 1377303 (The Pile)

Max Activating Token Index: 829

Text #2

Max Range: 1.1258. Min Range: -1.1258

Max Act: 0.9644. Min Act: -0.0000

Data Index: 1811913 (The Pile)

Max Activating Token Index: 922

Text #3

Max Range: 1.1258. Min Range: -1.1258

Max Act: 0.9609. Min Act: -0.0000

Data Index: 1898371 (The Pile)

Max Activating Token Index: 1013

Text #4

Max Range: 1.1258. Min Range: -1.1258

Max Act: 0.8407. Min Act: -0.0000

Data Index: 1256967 (The Pile)

Max Activating Token Index: 601

Text #5

Max Range: 1.1258. Min Range: -1.1258

Max Act: 0.8358. Min Act: 0.0000

Data Index: 1471159 (The Pile)

Max Activating Token Index: 879

Text #6

Max Range: 1.1258. Min Range: -1.1258

Max Act: 0.8289. Min Act: -0.0000

Data Index: 40714 (The Pile)

Max Activating Token Index: 630

Text #7

Max Range: 1.1258. Min Range: -1.1258

Max Act: 0.8445. Min Act: -0.0000

Data Index: 282616 (The Pile)

Max Activating Token Index: 641

Text #8

Max Range: 1.1258. Min Range: -1.1258

Max Act: 0.9145. Min Act: -0.0000

Data Index: 1707905 (The Pile)

Max Activating Token Index: 483

Text #9

Max Range: 1.1258. Min Range: -1.1258

Max Act: 0.8398. Min Act: -0.0000

Data Index: 1868296 (The Pile)

Max Activating Token Index: 490

Text #10

Max Range: 1.1258. Min Range: -1.1258

Max Act: 0.8701. Min Act: -0.0000

Data Index: 25778 (The Pile)

Max Activating Token Index: 733

Text #11

Max Range: 1.1258. Min Range: -1.1258

Max Act: 0.7963. Min Act: -0.0000

Data Index: 54259 (The Pile)

Max Activating Token Index: 527

Text #12

Max Range: 1.1258. Min Range: -1.1258

Max Act: 0.8439. Min Act: -0.0000

Data Index: 178076 (The Pile)

Max Activating Token Index: 349

Text #13

Max Range: 1.1258. Min Range: -1.1258

Max Act: 0.8156. Min Act: -0.0000

Data Index: 1719137 (The Pile)

Max Activating Token Index: 991

Text #14

Max Range: 1.1258. Min Range: -1.1258

Max Act: 0.8562. Min Act: -0.0000

Data Index: 785300 (The Pile)

Max Activating Token Index: 689

Text #15

Max Range: 1.1258. Min Range: -1.1258

Max Act: 0.7629. Min Act: -0.0000

Data Index: 1832717 (The Pile)

Max Activating Token Index: 883

Text #16

Max Range: 1.1258. Min Range: -1.1258

Max Act: 0.8515. Min Act: -0.0000

Data Index: 1471705 (The Pile)

Max Activating Token Index: 697

Text #17

Max Range: 1.1258. Min Range: -1.1258

Max Act: 0.8647. Min Act: -0.0000

Data Index: 479393 (The Pile)

Max Activating Token Index: 630

Text #18

Max Range: 1.1258. Min Range: -1.1258

Max Act: 0.8423. Min Act: -0.0000

Data Index: 1601715 (The Pile)

Max Activating Token Index: 657

Text #19

Max Range: 1.1258. Min Range: -1.1258

Max Act: 0.8195. Min Act: -0.0000

Data Index: 1339341 (The Pile)

Max Activating Token Index: 880