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

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

Neuron 3614 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: 0.4667. Min Range: -0.4667

Max Act: 0.4667. Min Act: -0.0000

Data Index: 449858 (C4 (Web Text))

Max Activating Token Index: 530

Text #1

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.4363. Min Act: -0.0001

Data Index: 160635 (C4 (Web Text))

Max Activating Token Index: 491

Text #2

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.4499. Min Act: -0.0000

Data Index: 980700 (C4 (Web Text))

Max Activating Token Index: 563

Text #3

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.3881. Min Act: -0.0001

Data Index: 230201 (C4 (Web Text))

Max Activating Token Index: 557

Text #4

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.4281. Min Act: -0.0000

Data Index: 32617 (C4 (Web Text))

Max Activating Token Index: 207

Text #5

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.4165. Min Act: -0.0000

Data Index: 683282 (C4 (Web Text))

Max Activating Token Index: 776

Text #6

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.3714. Min Act: -0.0000

Data Index: 109384 (C4 (Web Text))

Max Activating Token Index: 680

Text #7

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.3982. Min Act: -0.0000

Data Index: 69024 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.3872. Min Act: -0.0001

Data Index: 1307887 (C4 (Web Text))

Max Activating Token Index: 485

Text #9

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.3871. Min Act: -0.0000

Data Index: 839748 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.4126. Min Act: -0.0000

Data Index: 605371 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.3826. Min Act: -0.0000

Data Index: 392290 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.3711. Min Act: -0.0000

Data Index: 626888 (C4 (Web Text))

Max Activating Token Index: 951

Text #13

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.3965. Min Act: -0.0001

Data Index: 259666 (C4 (Web Text))

Max Activating Token Index: 468

Text #14

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.3860. Min Act: -0.0001

Data Index: 306982 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.3748. Min Act: -0.0000

Data Index: 337649 (C4 (Web Text))

Max Activating Token Index: 432

Text #16

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.3699. Min Act: -0.0001

Data Index: 1208147 (C4 (Web Text))

Max Activating Token Index: 966

Text #17

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.3702. Min Act: -0.0000

Data Index: 1338870 (C4 (Web Text))

Max Activating Token Index: 364

Text #18

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.3698. Min Act: -0.0001

Data Index: 1148982 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.3784. Min Act: -0.0001

Data Index: 514060 (C4 (Web Text))

Max Activating Token Index: 713