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

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

Neuron 2147 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5087. Min Range: -0.5087

Max Act: 0.5087. Min Act: -0.0000

Data Index: 960487 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 0.5087. Min Range: -0.5087

Max Act: 0.4610. Min Act: -0.0000

Data Index: 406571 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 0.5087. Min Range: -0.5087

Max Act: 0.4133. Min Act: -0.0000

Data Index: 1008758 (C4 (Web Text))

Max Activating Token Index: 99

Text #3

Max Range: 0.5087. Min Range: -0.5087

Max Act: 0.4253. Min Act: -0.0000

Data Index: 767228 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 0.5087. Min Range: -0.5087

Max Act: 0.4112. Min Act: -0.0000

Data Index: 1310261 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 0.5087. Min Range: -0.5087

Max Act: 0.4256. Min Act: -0.0000

Data Index: 658343 (C4 (Web Text))

Max Activating Token Index: 796

Text #6

Max Range: 0.5087. Min Range: -0.5087

Max Act: 0.3984. Min Act: -0.0000

Data Index: 544957 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 0.5087. Min Range: -0.5087

Max Act: 0.3723. Min Act: -0.0000

Data Index: 967833 (C4 (Web Text))

Max Activating Token Index: 801

Text #8

Max Range: 0.5087. Min Range: -0.5087

Max Act: 0.3757. Min Act: -0.0000

Data Index: 785179 (C4 (Web Text))

Max Activating Token Index: 559

Text #9

Max Range: 0.5087. Min Range: -0.5087

Max Act: 0.3835. Min Act: -0.0000

Data Index: 1167904 (C4 (Web Text))

Max Activating Token Index: 82

Text #10

Max Range: 0.5087. Min Range: -0.5087

Max Act: 0.3800. Min Act: -0.0000

Data Index: 1304039 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 0.5087. Min Range: -0.5087

Max Act: 0.3543. Min Act: 0.0000

Data Index: 120690 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 0.5087. Min Range: -0.5087

Max Act: 0.3540. Min Act: -0.0000

Data Index: 694006 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 0.5087. Min Range: -0.5087

Max Act: 0.3532. Min Act: -0.0000

Data Index: 12913 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 0.5087. Min Range: -0.5087

Max Act: 0.3744. Min Act: -0.0000

Data Index: 251326 (C4 (Web Text))

Max Activating Token Index: 640

Text #15

Max Range: 0.5087. Min Range: -0.5087

Max Act: 0.3632. Min Act: -0.0000

Data Index: 697985 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 0.5087. Min Range: -0.5087

Max Act: 0.3507. Min Act: -0.0000

Data Index: 938289 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 0.5087. Min Range: -0.5087

Max Act: 0.3374. Min Act: -0.0000

Data Index: 858893 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 0.5087. Min Range: -0.5087

Max Act: 0.3312. Min Act: -0.0000

Data Index: 541595 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 0.5087. Min Range: -0.5087

Max Act: 0.3557. Min Act: -0.0000

Data Index: 472238 (C4 (Web Text))

Max Activating Token Index: 614