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

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

Neuron 786 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2654. Min Range: -1.2654

Max Act: 1.2654. Min Act: -0.0000

Data Index: 566774 (C4 (Web Text))

Max Activating Token Index: 246

Text #1

Max Range: 1.2654. Min Range: -1.2654

Max Act: 0.8573. Min Act: -0.0000

Data Index: 45751 (C4 (Web Text))

Max Activating Token Index: 723

Text #2

Max Range: 1.2654. Min Range: -1.2654

Max Act: 0.8238. Min Act: -0.0000

Data Index: 282327 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 1.2654. Min Range: -1.2654

Max Act: 0.8354. Min Act: -0.0000

Data Index: 54535 (C4 (Web Text))

Max Activating Token Index: 861

Text #4

Max Range: 1.2654. Min Range: -1.2654

Max Act: 0.7830. Min Act: -0.0000

Data Index: 749307 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 1.2654. Min Range: -1.2654

Max Act: 0.8327. Min Act: -0.0000

Data Index: 480093 (C4 (Web Text))

Max Activating Token Index: 533

Text #6

Max Range: 1.2654. Min Range: -1.2654

Max Act: 0.8040. Min Act: -0.0000

Data Index: 909660 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 1.2654. Min Range: -1.2654

Max Act: 0.8001. Min Act: -0.0000

Data Index: 1119015 (C4 (Web Text))

Max Activating Token Index: 891

Text #8

Max Range: 1.2654. Min Range: -1.2654

Max Act: 0.7510. Min Act: -0.0000

Data Index: 245022 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 1.2654. Min Range: -1.2654

Max Act: 0.7923. Min Act: -0.0000

Data Index: 841049 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 1.2654. Min Range: -1.2654

Max Act: 0.7914. Min Act: -0.0000

Data Index: 665340 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 1.2654. Min Range: -1.2654

Max Act: 0.7849. Min Act: -0.0000

Data Index: 1074238 (C4 (Web Text))

Max Activating Token Index: 911

Text #12

Max Range: 1.2654. Min Range: -1.2654

Max Act: 0.8149. Min Act: -0.0000

Data Index: 1078936 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 1.2654. Min Range: -1.2654

Max Act: 0.7621. Min Act: -0.0000

Data Index: 470089 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 1.2654. Min Range: -1.2654

Max Act: 0.7603. Min Act: -0.0000

Data Index: 566875 (C4 (Web Text))

Max Activating Token Index: 162

Text #15

Max Range: 1.2654. Min Range: -1.2654

Max Act: 0.7635. Min Act: -0.0000

Data Index: 730684 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 1.2654. Min Range: -1.2654

Max Act: 0.7885. Min Act: -0.0000

Data Index: 1084688 (C4 (Web Text))

Max Activating Token Index: 73

Text #17

Max Range: 1.2654. Min Range: -1.2654

Max Act: 0.7841. Min Act: -0.0000

Data Index: 1264442 (C4 (Web Text))

Max Activating Token Index: 837

Text #18

Max Range: 1.2654. Min Range: -1.2654

Max Act: 0.8139. Min Act: -0.0000

Data Index: 1321282 (C4 (Web Text))

Max Activating Token Index: 711

Text #19

Max Range: 1.2654. Min Range: -1.2654

Max Act: 0.8239. Min Act: -0.0000

Data Index: 360584 (C4 (Web Text))

Max Activating Token Index: 846