Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 236 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.6782. Min Act: -0.0000

Data Index: 621013 (C4 (Web Text))

Max Activating Token Index: 558

Text #1

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.6840. Min Act: -0.0000

Data Index: 552775 (C4 (Web Text))

Max Activating Token Index: 479

Text #2

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.6794. Min Act: -0.0000

Data Index: 292342 (C4 (Web Text))

Max Activating Token Index: 156

Text #3

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.6625. Min Act: -0.0000

Data Index: 748167 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.6044. Min Act: -0.0000

Data Index: 633070 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.6063. Min Act: -0.0000

Data Index: 30555 (C4 (Web Text))

Max Activating Token Index: 387

Text #6

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.5966. Min Act: -0.0000

Data Index: 368442 (C4 (Web Text))

Max Activating Token Index: 1005

Text #7

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.5729. Min Act: -0.0000

Data Index: 227787 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.5802. Min Act: -0.0000

Data Index: 208360 (C4 (Web Text))

Max Activating Token Index: 279

Text #9

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.5787. Min Act: -0.0000

Data Index: 192282 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.5525. Min Act: -0.0000

Data Index: 1148618 (C4 (Web Text))

Max Activating Token Index: 415

Text #11

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.5424. Min Act: -0.0000

Data Index: 882102 (C4 (Web Text))

Max Activating Token Index: 843

Text #12

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.5558. Min Act: -0.0000

Data Index: 967681 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.5049. Min Act: -0.0000

Data Index: 43101 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.4862. Min Act: -0.0000

Data Index: 427384 (C4 (Web Text))

Max Activating Token Index: 403

Text #15

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.5049. Min Act: -0.0000

Data Index: 1347462 (C4 (Web Text))

Max Activating Token Index: 768

Text #16

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.5002. Min Act: -0.0000

Data Index: 914211 (C4 (Web Text))

Max Activating Token Index: 423

Text #17

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.4929. Min Act: -0.0000

Data Index: 829300 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.4909. Min Act: -0.0000

Data Index: 384388 (C4 (Web Text))

Max Activating Token Index: 569

Text #19

Max Range: 0.6840. Min Range: -0.6840

Max Act: 0.5055. Min Act: -0.0000

Data Index: 837830 (C4 (Web Text))

Max Activating Token Index: 455