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

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

Neuron 4630 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6663. Min Range: -1.6663

Max Act: 1.6663. Min Act: -0.0000

Data Index: 406692 (C4 (Web Text))

Max Activating Token Index: 900

Text #1

Max Range: 1.6663. Min Range: -1.6663

Max Act: 1.1531. Min Act: -0.0000

Data Index: 1111091 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 1.6663. Min Range: -1.6663

Max Act: 0.9015. Min Act: -0.0000

Data Index: 761127 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 1.6663. Min Range: -1.6663

Max Act: 0.9351. Min Act: -0.0000

Data Index: 878500 (C4 (Web Text))

Max Activating Token Index: 960

Text #4

Max Range: 1.6663. Min Range: -1.6663

Max Act: 0.8931. Min Act: -0.0000

Data Index: 769302 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 1.6663. Min Range: -1.6663

Max Act: 0.9027. Min Act: -0.0000

Data Index: 235277 (C4 (Web Text))

Max Activating Token Index: 945

Text #6

Max Range: 1.6663. Min Range: -1.6663

Max Act: 0.8824. Min Act: -0.0000

Data Index: 235354 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 1.6663. Min Range: -1.6663

Max Act: 0.8512. Min Act: -0.0000

Data Index: 398933 (C4 (Web Text))

Max Activating Token Index: 960

Text #8

Max Range: 1.6663. Min Range: -1.6663

Max Act: 0.8403. Min Act: -0.0000

Data Index: 912160 (C4 (Web Text))

Max Activating Token Index: 587

Text #9

Max Range: 1.6663. Min Range: -1.6663

Max Act: 0.8422. Min Act: -0.0000

Data Index: 409750 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 1.6663. Min Range: -1.6663

Max Act: 0.8344. Min Act: -0.0000

Data Index: 467877 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 1.6663. Min Range: -1.6663

Max Act: 0.7777. Min Act: -0.0000

Data Index: 737578 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 1.6663. Min Range: -1.6663

Max Act: 0.8012. Min Act: -0.0000

Data Index: 816177 (C4 (Web Text))

Max Activating Token Index: 1020

Text #13

Max Range: 1.6663. Min Range: -1.6663

Max Act: 0.7923. Min Act: -0.0000

Data Index: 645520 (C4 (Web Text))

Max Activating Token Index: 953

Text #14

Max Range: 1.6663. Min Range: -1.6663

Max Act: 0.7945. Min Act: -0.0000

Data Index: 725836 (C4 (Web Text))

Max Activating Token Index: 75

Text #15

Max Range: 1.6663. Min Range: -1.6663

Max Act: 0.8158. Min Act: -0.0000

Data Index: 1007662 (C4 (Web Text))

Max Activating Token Index: 11

Text #16

Max Range: 1.6663. Min Range: -1.6663

Max Act: 0.7663. Min Act: -0.0000

Data Index: 489767 (C4 (Web Text))

Max Activating Token Index: 432

Text #17

Max Range: 1.6663. Min Range: -1.6663

Max Act: 0.7581. Min Act: -0.0000

Data Index: 903700 (C4 (Web Text))

Max Activating Token Index: 986

Text #18

Max Range: 1.6663. Min Range: -1.6663

Max Act: 0.7462. Min Act: -0.0000

Data Index: 1194418 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 1.6663. Min Range: -1.6663

Max Act: 0.7447. Min Act: -0.0000

Data Index: 540311 (C4 (Web Text))

Max Activating Token Index: 771