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

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

Neuron 1939 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: 2.1530. Min Range: -2.1530

Max Act: 2.1530. Min Act: -0.0000

Data Index: 903363 (C4 (Web Text))

Max Activating Token Index: 504

Text #1

Max Range: 2.1530. Min Range: -2.1530

Max Act: 1.7603. Min Act: -0.0000

Data Index: 1536497 (Python Code)

Max Activating Token Index: 710

Text #2

Max Range: 2.1530. Min Range: -2.1530

Max Act: 1.9466. Min Act: -0.0000

Data Index: 225838 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 2.1530. Min Range: -2.1530

Max Act: 1.6401. Min Act: -0.0000

Data Index: 175312 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 2.1530. Min Range: -2.1530

Max Act: 1.8135. Min Act: -0.0000

Data Index: 993991 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 2.1530. Min Range: -2.1530

Max Act: 1.6909. Min Act: -0.0000

Data Index: 1443661 (Python Code)

Max Activating Token Index: 434

Text #6

Max Range: 2.1530. Min Range: -2.1530

Max Act: 1.6932. Min Act: -0.0000

Data Index: 501279 (C4 (Web Text))

Max Activating Token Index: 746

Text #7

Max Range: 2.1530. Min Range: -2.1530

Max Act: 1.4746. Min Act: -0.0000

Data Index: 1015591 (C4 (Web Text))

Max Activating Token Index: 798

Text #8

Max Range: 2.1530. Min Range: -2.1530

Max Act: 1.6613. Min Act: -0.0000

Data Index: 272012 (C4 (Web Text))

Max Activating Token Index: 195

Text #9

Max Range: 2.1530. Min Range: -2.1530

Max Act: 1.5945. Min Act: -0.0000

Data Index: 1097931 (C4 (Web Text))

Max Activating Token Index: 942

Text #10

Max Range: 2.1530. Min Range: -2.1530

Max Act: 1.5718. Min Act: -0.0000

Data Index: 1061915 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 2.1530. Min Range: -2.1530

Max Act: 1.5501. Min Act: -0.0000

Data Index: 790822 (C4 (Web Text))

Max Activating Token Index: 463

Text #12

Max Range: 2.1530. Min Range: -2.1530

Max Act: 1.3605. Min Act: -0.0000

Data Index: 1351948 (C4 (Web Text))

Max Activating Token Index: 239

Text #13

Max Range: 2.1530. Min Range: -2.1530

Max Act: 1.5502. Min Act: -0.0000

Data Index: 46246 (C4 (Web Text))

Max Activating Token Index: 867

Text #14

Max Range: 2.1530. Min Range: -2.1530

Max Act: 1.5468. Min Act: -0.0000

Data Index: 100865 (C4 (Web Text))

Max Activating Token Index: 610

Text #15

Max Range: 2.1530. Min Range: -2.1530

Max Act: 1.4353. Min Act: -0.0000

Data Index: 828639 (C4 (Web Text))

Max Activating Token Index: 773

Text #16

Max Range: 2.1530. Min Range: -2.1530

Max Act: 1.4723. Min Act: -0.0000

Data Index: 933463 (C4 (Web Text))

Max Activating Token Index: 240

Text #17

Max Range: 2.1530. Min Range: -2.1530

Max Act: 1.3834. Min Act: -0.0000

Data Index: 785073 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 2.1530. Min Range: -2.1530

Max Act: 1.3728. Min Act: -0.0000

Data Index: 595767 (C4 (Web Text))

Max Activating Token Index: 864

Text #19

Max Range: 2.1530. Min Range: -2.1530

Max Act: 1.5398. Min Act: -0.0000

Data Index: 574046 (C4 (Web Text))

Max Activating Token Index: 422