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

Dataset: The Pile

Neuron 1342 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4062. Min Range: -3.4062

Max Act: 3.4062. Min Act: -0.0000

Data Index: 576636 (The Pile)

Max Activating Token Index: 540

Text #1

Max Range: 3.4062. Min Range: -3.4062

Max Act: 3.2255. Min Act: -0.0000

Data Index: 1079614 (The Pile)

Max Activating Token Index: 571

Text #2

Max Range: 3.4062. Min Range: -3.4062

Max Act: 3.1874. Min Act: -0.0000

Data Index: 414029 (The Pile)

Max Activating Token Index: 351

Text #3

Max Range: 3.4062. Min Range: -3.4062

Max Act: 2.8082. Min Act: -0.0000

Data Index: 612383 (The Pile)

Max Activating Token Index: 188

Text #4

Max Range: 3.4062. Min Range: -3.4062

Max Act: 2.7598. Min Act: -0.0000

Data Index: 425433 (The Pile)

Max Activating Token Index: 296

Text #5

Max Range: 3.4062. Min Range: -3.4062

Max Act: 2.8598. Min Act: -0.0000

Data Index: 1488405 (The Pile)

Max Activating Token Index: 586

Text #6

Max Range: 3.4062. Min Range: -3.4062

Max Act: 2.7923. Min Act: -0.0000

Data Index: 1341246 (The Pile)

Max Activating Token Index: 816

Text #7

Max Range: 3.4062. Min Range: -3.4062

Max Act: 2.8588. Min Act: -0.0000

Data Index: 1660006 (The Pile)

Max Activating Token Index: 826

Text #8

Max Range: 3.4062. Min Range: -3.4062

Max Act: 2.7969. Min Act: -0.0000

Data Index: 1310031 (The Pile)

Max Activating Token Index: 413

Text #9

Max Range: 3.4062. Min Range: -3.4062

Max Act: 2.4716. Min Act: -0.0000

Data Index: 969343 (The Pile)

Max Activating Token Index: 508

Text #10

Max Range: 3.4062. Min Range: -3.4062

Max Act: 2.4484. Min Act: -0.0000

Data Index: 843076 (The Pile)

Max Activating Token Index: 1015

Text #11

Max Range: 3.4062. Min Range: -3.4062

Max Act: 2.5557. Min Act: -0.0000

Data Index: 1554388 (The Pile)

Max Activating Token Index: 183

Text #12

Max Range: 3.4062. Min Range: -3.4062

Max Act: 2.2853. Min Act: -0.0000

Data Index: 555706 (The Pile)

Max Activating Token Index: 654

Text #13

Max Range: 3.4062. Min Range: -3.4062

Max Act: 2.4056. Min Act: -0.0000

Data Index: 999009 (The Pile)

Max Activating Token Index: 444

Text #14

Max Range: 3.4062. Min Range: -3.4062

Max Act: 2.6155. Min Act: -0.0000

Data Index: 1375583 (The Pile)

Max Activating Token Index: 895

Text #15

Max Range: 3.4062. Min Range: -3.4062

Max Act: 2.4509. Min Act: -0.0000

Data Index: 1879666 (The Pile)

Max Activating Token Index: 291

Text #16

Max Range: 3.4062. Min Range: -3.4062

Max Act: 2.2297. Min Act: -0.0000

Data Index: 1104920 (The Pile)

Max Activating Token Index: 975

Text #17

Max Range: 3.4062. Min Range: -3.4062

Max Act: 2.6817. Min Act: -0.0000

Data Index: 598895 (The Pile)

Max Activating Token Index: 14

Text #18

Max Range: 3.4062. Min Range: -3.4062

Max Act: 2.6059. Min Act: -0.0000

Data Index: 780591 (The Pile)

Max Activating Token Index: 454

Text #19

Max Range: 3.4062. Min Range: -3.4062

Max Act: 2.4874. Min Act: -0.0000

Data Index: 1429503 (The Pile)

Max Activating Token Index: 234