Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4860 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3393. Min Range: -1.3393

Max Act: 1.3393. Min Act: -0.0000

Data Index: 581830 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 1.3393. Min Range: -1.3393

Max Act: 1.1460. Min Act: 0.0003

Data Index: 509820 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 1.3393. Min Range: -1.3393

Max Act: 1.1727. Min Act: 0.0001

Data Index: 1073363 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 1.3393. Min Range: -1.3393

Max Act: 1.1023. Min Act: -0.0000

Data Index: 655137 (C4 (Web Text))

Max Activating Token Index: 763

Text #4

Max Range: 1.3393. Min Range: -1.3393

Max Act: 0.9307. Min Act: -0.0000

Data Index: 755779 (C4 (Web Text))

Max Activating Token Index: 70

Text #5

Max Range: 1.3393. Min Range: -1.3393

Max Act: 0.8130. Min Act: -0.0000

Data Index: 801368 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 1.3393. Min Range: -1.3393

Max Act: 0.7862. Min Act: -0.0000

Data Index: 732510 (C4 (Web Text))

Max Activating Token Index: 953

Text #7

Max Range: 1.3393. Min Range: -1.3393

Max Act: 0.8164. Min Act: -0.0000

Data Index: 1160640 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 1.3393. Min Range: -1.3393

Max Act: 0.7749. Min Act: -0.0000

Data Index: 294073 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 1.3393. Min Range: -1.3393

Max Act: 0.7328. Min Act: -0.0000

Data Index: 184330 (C4 (Web Text))

Max Activating Token Index: 731

Text #10

Max Range: 1.3393. Min Range: -1.3393

Max Act: 0.7236. Min Act: -0.0000

Data Index: 617721 (C4 (Web Text))

Max Activating Token Index: 603

Text #11

Max Range: 1.3393. Min Range: -1.3393

Max Act: 0.7873. Min Act: 0.0001

Data Index: 1216175 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 1.3393. Min Range: -1.3393

Max Act: 0.7249. Min Act: -0.0000

Data Index: 966823 (C4 (Web Text))

Max Activating Token Index: 409

Text #13

Max Range: 1.3393. Min Range: -1.3393

Max Act: 0.6798. Min Act: -0.0000

Data Index: 1018800 (C4 (Web Text))

Max Activating Token Index: 888

Text #14

Max Range: 1.3393. Min Range: -1.3393

Max Act: 0.7259. Min Act: -0.0000

Data Index: 523986 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 1.3393. Min Range: -1.3393

Max Act: 0.7665. Min Act: -0.0000

Data Index: 1312133 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 1.3393. Min Range: -1.3393

Max Act: 0.6943. Min Act: -0.0000

Data Index: 856537 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 1.3393. Min Range: -1.3393

Max Act: 0.7156. Min Act: 0.0000

Data Index: 1276960 (C4 (Web Text))

Max Activating Token Index: 1021

Text #18

Max Range: 1.3393. Min Range: -1.3393

Max Act: 0.7021. Min Act: -0.0000

Data Index: 201662 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 1.3393. Min Range: -1.3393

Max Act: 0.6488. Min Act: -0.0000

Data Index: 117477 (C4 (Web Text))

Max Activating Token Index: 994