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

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

Neuron 1573 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: 1.4167. Min Range: -1.4167

Max Act: 1.4167. Min Act: -0.0000

Data Index: 492218 (C4 (Web Text))

Max Activating Token Index: 636

Text #1

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.3074. Min Act: -0.0000

Data Index: 133766 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.3703. Min Act: -0.0000

Data Index: 495545 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.2558. Min Act: -0.0000

Data Index: 53152 (C4 (Web Text))

Max Activating Token Index: 822

Text #4

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.2392. Min Act: -0.0000

Data Index: 482488 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.1804. Min Act: -0.0000

Data Index: 662087 (C4 (Web Text))

Max Activating Token Index: 260

Text #6

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.2058. Min Act: -0.0000

Data Index: 954919 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.1223. Min Act: -0.0000

Data Index: 421320 (C4 (Web Text))

Max Activating Token Index: 321

Text #8

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.1308. Min Act: -0.0000

Data Index: 602861 (C4 (Web Text))

Max Activating Token Index: 696

Text #9

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.1988. Min Act: -0.0000

Data Index: 983246 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.0901. Min Act: -0.0000

Data Index: 1231764 (C4 (Web Text))

Max Activating Token Index: 790

Text #11

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.0796. Min Act: -0.0000

Data Index: 439088 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.0960. Min Act: -0.0000

Data Index: 584041 (C4 (Web Text))

Max Activating Token Index: 668

Text #13

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.0739. Min Act: -0.0000

Data Index: 613254 (C4 (Web Text))

Max Activating Token Index: 415

Text #14

Max Range: 1.4167. Min Range: -1.4167

Max Act: 0.9778. Min Act: -0.0000

Data Index: 239685 (C4 (Web Text))

Max Activating Token Index: 148

Text #15

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.0626. Min Act: -0.0000

Data Index: 371964 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.1124. Min Act: -0.0000

Data Index: 1232538 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 1.4167. Min Range: -1.4167

Max Act: 0.9913. Min Act: -0.0000

Data Index: 552744 (C4 (Web Text))

Max Activating Token Index: 314

Text #18

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.1000. Min Act: -0.0000

Data Index: 643258 (C4 (Web Text))

Max Activating Token Index: 685

Text #19

Max Range: 1.4167. Min Range: -1.4167

Max Act: 0.9989. Min Act: -0.0000

Data Index: 1174417 (C4 (Web Text))

Max Activating Token Index: 877