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

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

Neuron 1754 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5496. Min Range: -0.5496

Max Act: 0.5496. Min Act: -0.0000

Data Index: 871671 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 0.5496. Min Range: -0.5496

Max Act: 0.4756. Min Act: -0.0000

Data Index: 803074 (C4 (Web Text))

Max Activating Token Index: 898

Text #2

Max Range: 0.5496. Min Range: -0.5496

Max Act: 0.4756. Min Act: -0.0000

Data Index: 658306 (C4 (Web Text))

Max Activating Token Index: 581

Text #3

Max Range: 0.5496. Min Range: -0.5496

Max Act: 0.4727. Min Act: -0.0000

Data Index: 933835 (C4 (Web Text))

Max Activating Token Index: 955

Text #4

Max Range: 0.5496. Min Range: -0.5496

Max Act: 0.4907. Min Act: -0.0000

Data Index: 375912 (C4 (Web Text))

Max Activating Token Index: 662

Text #5

Max Range: 0.5496. Min Range: -0.5496

Max Act: 0.4657. Min Act: -0.0000

Data Index: 754894 (C4 (Web Text))

Max Activating Token Index: 352

Text #6

Max Range: 0.5496. Min Range: -0.5496

Max Act: 0.4677. Min Act: -0.0000

Data Index: 1108441 (C4 (Web Text))

Max Activating Token Index: 301

Text #7

Max Range: 0.5496. Min Range: -0.5496

Max Act: 0.4416. Min Act: -0.0000

Data Index: 718366 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 0.5496. Min Range: -0.5496

Max Act: 0.4343. Min Act: -0.0000

Data Index: 530161 (C4 (Web Text))

Max Activating Token Index: 799

Text #9

Max Range: 0.5496. Min Range: -0.5496

Max Act: 0.4284. Min Act: -0.0000

Data Index: 1087747 (C4 (Web Text))

Max Activating Token Index: 634

Text #10

Max Range: 0.5496. Min Range: -0.5496

Max Act: 0.4279. Min Act: -0.0000

Data Index: 695969 (C4 (Web Text))

Max Activating Token Index: 24

Text #11

Max Range: 0.5496. Min Range: -0.5496

Max Act: 0.4129. Min Act: -0.0000

Data Index: 853299 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 0.5496. Min Range: -0.5496

Max Act: 0.4126. Min Act: -0.0000

Data Index: 239536 (C4 (Web Text))

Max Activating Token Index: 424

Text #13

Max Range: 0.5496. Min Range: -0.5496

Max Act: 0.4082. Min Act: -0.0000

Data Index: 1196916 (C4 (Web Text))

Max Activating Token Index: 640

Text #14

Max Range: 0.5496. Min Range: -0.5496

Max Act: 0.3880. Min Act: -0.0000

Data Index: 925785 (C4 (Web Text))

Max Activating Token Index: 99

Text #15

Max Range: 0.5496. Min Range: -0.5496

Max Act: 0.3762. Min Act: -0.0000

Data Index: 668270 (C4 (Web Text))

Max Activating Token Index: 229

Text #16

Max Range: 0.5496. Min Range: -0.5496

Max Act: 0.3695. Min Act: -0.0000

Data Index: 1638555 (Python Code)

Max Activating Token Index: 577

Text #17

Max Range: 0.5496. Min Range: -0.5496

Max Act: 0.3642. Min Act: -0.0000

Data Index: 342035 (C4 (Web Text))

Max Activating Token Index: 272

Text #18

Max Range: 0.5496. Min Range: -0.5496

Max Act: 0.3450. Min Act: 0.0000

Data Index: 338556 (C4 (Web Text))

Max Activating Token Index: 966

Text #19

Max Range: 0.5496. Min Range: -0.5496

Max Act: 0.3409. Min Act: -0.0000

Data Index: 842055 (C4 (Web Text))

Max Activating Token Index: 708