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

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

Neuron 2 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: 1.3233. Min Range: -1.3233

Max Act: 1.3233. Min Act: -0.0000

Data Index: 205245 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 1.3233. Min Range: -1.3233

Max Act: 1.2003. Min Act: -0.0000

Data Index: 1357788 (C4 (Web Text))

Max Activating Token Index: 489

Text #2

Max Range: 1.3233. Min Range: -1.3233

Max Act: 1.0855. Min Act: -0.0000

Data Index: 950683 (C4 (Web Text))

Max Activating Token Index: 473

Text #3

Max Range: 1.3233. Min Range: -1.3233

Max Act: 0.9739. Min Act: -0.0000

Data Index: 177046 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 1.3233. Min Range: -1.3233

Max Act: 0.9817. Min Act: -0.0000

Data Index: 992007 (C4 (Web Text))

Max Activating Token Index: 360

Text #5

Max Range: 1.3233. Min Range: -1.3233

Max Act: 0.9626. Min Act: -0.0000

Data Index: 1035811 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 1.3233. Min Range: -1.3233

Max Act: 0.9699. Min Act: -0.0000

Data Index: 260493 (C4 (Web Text))

Max Activating Token Index: 458

Text #7

Max Range: 1.3233. Min Range: -1.3233

Max Act: 0.9410. Min Act: -0.0000

Data Index: 1179625 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 1.3233. Min Range: -1.3233

Max Act: 0.9680. Min Act: -0.0000

Data Index: 5741 (C4 (Web Text))

Max Activating Token Index: 387

Text #9

Max Range: 1.3233. Min Range: -1.3233

Max Act: 0.9867. Min Act: -0.0000

Data Index: 809673 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 1.3233. Min Range: -1.3233

Max Act: 0.9767. Min Act: -0.0000

Data Index: 30687 (C4 (Web Text))

Max Activating Token Index: 3

Text #11

Max Range: 1.3233. Min Range: -1.3233

Max Act: 0.9137. Min Act: -0.0000

Data Index: 133844 (C4 (Web Text))

Max Activating Token Index: 465

Text #12

Max Range: 1.3233. Min Range: -1.3233

Max Act: 0.9070. Min Act: -0.0000

Data Index: 1002483 (C4 (Web Text))

Max Activating Token Index: 356

Text #13

Max Range: 1.3233. Min Range: -1.3233

Max Act: 0.9483. Min Act: -0.0000

Data Index: 846506 (C4 (Web Text))

Max Activating Token Index: 127

Text #14

Max Range: 1.3233. Min Range: -1.3233

Max Act: 0.9544. Min Act: -0.0000

Data Index: 571658 (C4 (Web Text))

Max Activating Token Index: 539

Text #15

Max Range: 1.3233. Min Range: -1.3233

Max Act: 0.8959. Min Act: -0.0000

Data Index: 728223 (C4 (Web Text))

Max Activating Token Index: 419

Text #16

Max Range: 1.3233. Min Range: -1.3233

Max Act: 0.9197. Min Act: -0.0000

Data Index: 322478 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 1.3233. Min Range: -1.3233

Max Act: 0.9548. Min Act: -0.0000

Data Index: 876978 (C4 (Web Text))

Max Activating Token Index: 413

Text #18

Max Range: 1.3233. Min Range: -1.3233

Max Act: 0.9172. Min Act: -0.0000

Data Index: 369669 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 1.3233. Min Range: -1.3233

Max Act: 0.9487. Min Act: -0.0000

Data Index: 450212 (C4 (Web Text))

Max Activating Token Index: 172