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

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

Neuron 1782 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: 0.4478. Min Range: -0.4478

Max Act: 0.4478. Min Act: -0.0000

Data Index: 1350680 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.4452. Min Act: -0.0000

Data Index: 333019 (C4 (Web Text))

Max Activating Token Index: 46

Text #2

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.4226. Min Act: -0.0000

Data Index: 631811 (C4 (Web Text))

Max Activating Token Index: 768

Text #3

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3970. Min Act: -0.0000

Data Index: 1065684 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.4087. Min Act: -0.0000

Data Index: 585310 (C4 (Web Text))

Max Activating Token Index: 843

Text #5

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3995. Min Act: -0.0000

Data Index: 174010 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3214. Min Act: -0.0000

Data Index: 199853 (C4 (Web Text))

Max Activating Token Index: 709

Text #7

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3848. Min Act: -0.0000

Data Index: 746748 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3376. Min Act: -0.0000

Data Index: 367791 (C4 (Web Text))

Max Activating Token Index: 181

Text #9

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3120. Min Act: -0.0000

Data Index: 1622113 (Python Code)

Max Activating Token Index: 418

Text #10

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3279. Min Act: -0.0000

Data Index: 1566973 (Python Code)

Max Activating Token Index: 587

Text #11

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3128. Min Act: -0.0000

Data Index: 205757 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3058. Min Act: -0.0000

Data Index: 1560091 (Python Code)

Max Activating Token Index: 696

Text #13

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3181. Min Act: -0.0000

Data Index: 1578859 (Python Code)

Max Activating Token Index: 309

Text #14

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.2838. Min Act: -0.0000

Data Index: 1467734 (Python Code)

Max Activating Token Index: 865

Text #15

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3104. Min Act: -0.0000

Data Index: 518768 (C4 (Web Text))

Max Activating Token Index: 997

Text #16

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.2618. Min Act: -0.0000

Data Index: 660494 (C4 (Web Text))

Max Activating Token Index: 922

Text #17

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.2783. Min Act: -0.0000

Data Index: 280987 (C4 (Web Text))

Max Activating Token Index: 1015

Text #18

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.2697. Min Act: -0.0000

Data Index: 1630751 (Python Code)

Max Activating Token Index: 738

Text #19

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.2948. Min Act: -0.0000

Data Index: 635185 (C4 (Web Text))

Max Activating Token Index: 530