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

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

Neuron 4133 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: 0.5533. Min Range: -0.5533

Max Act: 0.5533. Min Act: -0.0000

Data Index: 962579 (C4 (Web Text))

Max Activating Token Index: 776

Text #1

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.5408. Min Act: -0.0000

Data Index: 1156174 (C4 (Web Text))

Max Activating Token Index: 205

Text #2

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.5361. Min Act: -0.0000

Data Index: 39521 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4806. Min Act: -0.0000

Data Index: 1124863 (C4 (Web Text))

Max Activating Token Index: 918

Text #4

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4826. Min Act: -0.0000

Data Index: 642741 (C4 (Web Text))

Max Activating Token Index: 649

Text #5

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4777. Min Act: -0.0000

Data Index: 33005 (C4 (Web Text))

Max Activating Token Index: 419

Text #6

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4670. Min Act: -0.0000

Data Index: 524722 (C4 (Web Text))

Max Activating Token Index: 833

Text #7

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4291. Min Act: -0.0000

Data Index: 1003154 (C4 (Web Text))

Max Activating Token Index: 373

Text #8

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4549. Min Act: -0.0000

Data Index: 316229 (C4 (Web Text))

Max Activating Token Index: 644

Text #9

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4670. Min Act: -0.0000

Data Index: 863919 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4184. Min Act: -0.0000

Data Index: 170653 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4120. Min Act: -0.0000

Data Index: 832629 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4217. Min Act: -0.0000

Data Index: 491981 (C4 (Web Text))

Max Activating Token Index: 58

Text #13

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4108. Min Act: -0.0000

Data Index: 1073161 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4170. Min Act: -0.0000

Data Index: 910406 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4266. Min Act: -0.0000

Data Index: 1064795 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4100. Min Act: -0.0000

Data Index: 170692 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4103. Min Act: -0.0000

Data Index: 1207130 (C4 (Web Text))

Max Activating Token Index: 689

Text #18

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4197. Min Act: -0.0000

Data Index: 906964 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4169. Min Act: -0.0000

Data Index: 831088 (C4 (Web Text))

Max Activating Token Index: 722