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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 467 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5699. Min Range: -0.5699

Max Act: 0.5699. Min Act: -0.0000

Data Index: 1613611 (Python Code)

Max Activating Token Index: 531

Text #1

Max Range: 0.5699. Min Range: -0.5699

Max Act: 0.4073. Min Act: -0.0000

Data Index: 1478031 (Python Code)

Max Activating Token Index: 359

Text #2

Max Range: 0.5699. Min Range: -0.5699

Max Act: 0.3979. Min Act: -0.0000

Data Index: 1583794 (Python Code)

Max Activating Token Index: 926

Text #3

Max Range: 0.5699. Min Range: -0.5699

Max Act: 0.4010. Min Act: -0.0000

Data Index: 1418073 (Python Code)

Max Activating Token Index: 517

Text #4

Max Range: 0.5699. Min Range: -0.5699

Max Act: 0.4113. Min Act: -0.0000

Data Index: 1448938 (Python Code)

Max Activating Token Index: 829

Text #5

Max Range: 0.5699. Min Range: -0.5699

Max Act: 0.3795. Min Act: -0.0000

Data Index: 1613242 (Python Code)

Max Activating Token Index: 102

Text #6

Max Range: 0.5699. Min Range: -0.5699

Max Act: 0.3741. Min Act: -0.0000

Data Index: 1619933 (Python Code)

Max Activating Token Index: 506

Text #7

Max Range: 0.5699. Min Range: -0.5699

Max Act: 0.3660. Min Act: -0.0000

Data Index: 1515522 (Python Code)

Max Activating Token Index: 477

Text #8

Max Range: 0.5699. Min Range: -0.5699

Max Act: 0.3374. Min Act: -0.0000

Data Index: 1500365 (Python Code)

Max Activating Token Index: 496

Text #9

Max Range: 0.5699. Min Range: -0.5699

Max Act: 0.3246. Min Act: -0.0000

Data Index: 1566320 (Python Code)

Max Activating Token Index: 1022

Text #10

Max Range: 0.5699. Min Range: -0.5699

Max Act: 0.3233. Min Act: -0.0000

Data Index: 1503590 (Python Code)

Max Activating Token Index: 327

Text #11

Max Range: 0.5699. Min Range: -0.5699

Max Act: 0.3192. Min Act: -0.0000

Data Index: 1472990 (Python Code)

Max Activating Token Index: 999

Text #12

Max Range: 0.5699. Min Range: -0.5699

Max Act: 0.3148. Min Act: -0.0000

Data Index: 1414607 (Python Code)

Max Activating Token Index: 666

Text #13

Max Range: 0.5699. Min Range: -0.5699

Max Act: 0.3132. Min Act: -0.0000

Data Index: 1550283 (Python Code)

Max Activating Token Index: 233

Text #14

Max Range: 0.5699. Min Range: -0.5699

Max Act: 0.3127. Min Act: -0.0000

Data Index: 1613727 (Python Code)

Max Activating Token Index: 573

Text #15

Max Range: 0.5699. Min Range: -0.5699

Max Act: 0.2906. Min Act: -0.0000

Data Index: 1368278 (Python Code)

Max Activating Token Index: 344

Text #16

Max Range: 0.5699. Min Range: -0.5699

Max Act: 0.3084. Min Act: -0.0000

Data Index: 1517426 (Python Code)

Max Activating Token Index: 427

Text #17

Max Range: 0.5699. Min Range: -0.5699

Max Act: 0.3359. Min Act: -0.0000

Data Index: 1467055 (Python Code)

Max Activating Token Index: 123

Text #18

Max Range: 0.5699. Min Range: -0.5699

Max Act: 0.3027. Min Act: -0.0000

Data Index: 1384709 (Python Code)

Max Activating Token Index: 793

Text #19

Max Range: 0.5699. Min Range: -0.5699

Max Act: 0.3222. Min Act: -0.0000

Data Index: 1622643 (Python Code)

Max Activating Token Index: 634