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

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

Neuron 4566 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: 2.7697. Min Range: -2.7697

Max Act: 2.7697. Min Act: 0.0001

Data Index: 1398304 (Python Code)

Max Activating Token Index: 61

Text #1

Max Range: 2.7697. Min Range: -2.7697

Max Act: 1.6722. Min Act: -0.0000

Data Index: 505223 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 2.7697. Min Range: -2.7697

Max Act: 1.7811. Min Act: -0.0000

Data Index: 1423199 (Python Code)

Max Activating Token Index: 90

Text #3

Max Range: 2.7697. Min Range: -2.7697

Max Act: 1.6883. Min Act: 0.0001

Data Index: 1584823 (Python Code)

Max Activating Token Index: 299

Text #4

Max Range: 2.7697. Min Range: -2.7697

Max Act: 1.5510. Min Act: -0.0000

Data Index: 1014206 (C4 (Web Text))

Max Activating Token Index: 589

Text #5

Max Range: 2.7697. Min Range: -2.7697

Max Act: 1.6341. Min Act: -0.0000

Data Index: 1125686 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 2.7697. Min Range: -2.7697

Max Act: 1.4328. Min Act: 0.0000

Data Index: 1578013 (Python Code)

Max Activating Token Index: 196

Text #7

Max Range: 2.7697. Min Range: -2.7697

Max Act: 1.4562. Min Act: -0.0000

Data Index: 744348 (C4 (Web Text))

Max Activating Token Index: 285

Text #8

Max Range: 2.7697. Min Range: -2.7697

Max Act: 1.5083. Min Act: 0.0001

Data Index: 1505826 (Python Code)

Max Activating Token Index: 31

Text #9

Max Range: 2.7697. Min Range: -2.7697

Max Act: 1.4068. Min Act: -0.0000

Data Index: 1589413 (Python Code)

Max Activating Token Index: 279

Text #10

Max Range: 2.7697. Min Range: -2.7697

Max Act: 1.4459. Min Act: -0.0000

Data Index: 1199770 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 2.7697. Min Range: -2.7697

Max Act: 1.3232. Min Act: 0.0001

Data Index: 1501208 (Python Code)

Max Activating Token Index: 446

Text #12

Max Range: 2.7697. Min Range: -2.7697

Max Act: 1.3369. Min Act: 0.0000

Data Index: 1602768 (Python Code)

Max Activating Token Index: 147

Text #13

Max Range: 2.7697. Min Range: -2.7697

Max Act: 1.3030. Min Act: -0.0000

Data Index: 445156 (C4 (Web Text))

Max Activating Token Index: 642

Text #14

Max Range: 2.7697. Min Range: -2.7697

Max Act: 1.2853. Min Act: -0.0000

Data Index: 456005 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 2.7697. Min Range: -2.7697

Max Act: 1.3011. Min Act: -0.0000

Data Index: 122682 (C4 (Web Text))

Max Activating Token Index: 517

Text #16

Max Range: 2.7697. Min Range: -2.7697

Max Act: 1.1509. Min Act: 0.0001

Data Index: 1496578 (Python Code)

Max Activating Token Index: 381

Text #17

Max Range: 2.7697. Min Range: -2.7697

Max Act: 1.1611. Min Act: 0.0001

Data Index: 1524151 (Python Code)

Max Activating Token Index: 26

Text #18

Max Range: 2.7697. Min Range: -2.7697

Max Act: 1.1672. Min Act: 0.0000

Data Index: 1633822 (Python Code)

Max Activating Token Index: 125

Text #19

Max Range: 2.7697. Min Range: -2.7697

Max Act: 1.0745. Min Act: 0.0001

Data Index: 1425355 (Python Code)

Max Activating Token Index: 95