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

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

Neuron 60 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.6706. Min Act: -0.0003

Data Index: 786472 (C4 (Web Text))

Max Activating Token Index: 804

Text #1

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.6546. Min Act: -0.0003

Data Index: 1270804 (C4 (Web Text))

Max Activating Token Index: 543

Text #2

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5832. Min Act: -0.0003

Data Index: 1344974 (C4 (Web Text))

Max Activating Token Index: 654

Text #3

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5832. Min Act: -0.0003

Data Index: 494826 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5812. Min Act: -0.0003

Data Index: 1041477 (C4 (Web Text))

Max Activating Token Index: 264

Text #5

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5723. Min Act: -0.0003

Data Index: 353432 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5350. Min Act: -0.0003

Data Index: 850780 (C4 (Web Text))

Max Activating Token Index: 456

Text #7

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5693. Min Act: -0.0003

Data Index: 1096547 (C4 (Web Text))

Max Activating Token Index: 395

Text #8

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5672. Min Act: -0.0003

Data Index: 183887 (C4 (Web Text))

Max Activating Token Index: 657

Text #9

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5157. Min Act: -0.0003

Data Index: 1003353 (C4 (Web Text))

Max Activating Token Index: 566

Text #10

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5416. Min Act: -0.0003

Data Index: 772719 (C4 (Web Text))

Max Activating Token Index: 537

Text #11

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5396. Min Act: -0.0003

Data Index: 564106 (C4 (Web Text))

Max Activating Token Index: 19

Text #12

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5021. Min Act: -0.0003

Data Index: 287160 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.4992. Min Act: -0.0003

Data Index: 847964 (C4 (Web Text))

Max Activating Token Index: 295

Text #14

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.4992. Min Act: -0.0003

Data Index: 661396 (C4 (Web Text))

Max Activating Token Index: 660

Text #15

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.4979. Min Act: -0.0003

Data Index: 5530 (C4 (Web Text))

Max Activating Token Index: 705

Text #16

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.4970. Min Act: -0.0003

Data Index: 385848 (C4 (Web Text))

Max Activating Token Index: 871

Text #17

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.4921. Min Act: -0.0003

Data Index: 962270 (C4 (Web Text))

Max Activating Token Index: 304

Text #18

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.4834. Min Act: -0.0003

Data Index: 255572 (C4 (Web Text))

Max Activating Token Index: 955

Text #19

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.4837. Min Act: -0.0003

Data Index: 199631 (C4 (Web Text))

Max Activating Token Index: 355