Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2192 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.1073. Min Act: -0.0001

Data Index: 226725 (C4 (Web Text))

Max Activating Token Index: 586

Text #1

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.1106. Min Act: -0.0001

Data Index: 832250 (C4 (Web Text))

Max Activating Token Index: 437

Text #2

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0994. Min Act: -0.0000

Data Index: 1278398 (C4 (Web Text))

Max Activating Token Index: 407

Text #3

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0990. Min Act: -0.0000

Data Index: 216112 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0952. Min Act: -0.0001

Data Index: 1143490 (C4 (Web Text))

Max Activating Token Index: 926

Text #5

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0831. Min Act: -0.0001

Data Index: 1059248 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0723. Min Act: -0.0001

Data Index: 1552066 (Python Code)

Max Activating Token Index: 432

Text #7

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0693. Min Act: -0.0001

Data Index: 358713 (C4 (Web Text))

Max Activating Token Index: 513

Text #8

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0705. Min Act: -0.0001

Data Index: 813459 (C4 (Web Text))

Max Activating Token Index: 576

Text #9

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0656. Min Act: -0.0001

Data Index: 357160 (C4 (Web Text))

Max Activating Token Index: 497

Text #10

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0699. Min Act: -0.0001

Data Index: 1603300 (Python Code)

Max Activating Token Index: 137

Text #11

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0660. Min Act: -0.0000

Data Index: 594616 (C4 (Web Text))

Max Activating Token Index: 554

Text #12

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0590. Min Act: -0.0000

Data Index: 931192 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0651. Min Act: -0.0000

Data Index: 1043991 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0653. Min Act: -0.0001

Data Index: 109805 (C4 (Web Text))

Max Activating Token Index: 610

Text #15

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0619. Min Act: -0.0001

Data Index: 1372880 (Python Code)

Max Activating Token Index: 315

Text #16

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0665. Min Act: -0.0001

Data Index: 1072163 (C4 (Web Text))

Max Activating Token Index: 469

Text #17

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0659. Min Act: -0.0001

Data Index: 1374664 (Python Code)

Max Activating Token Index: 138

Text #18

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0602. Min Act: -0.0001

Data Index: 590844 (C4 (Web Text))

Max Activating Token Index: 734

Text #19

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0623. Min Act: -0.0001

Data Index: 220850 (C4 (Web Text))

Max Activating Token Index: 649