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

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

Neuron 4298 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.4234. Min Act: -0.0000

Data Index: 734119 (C4 (Web Text))

Max Activating Token Index: 1021

Text #1

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.4452. Min Act: -0.0000

Data Index: 457369 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.3816. Min Act: -0.0000

Data Index: 127852 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.3781. Min Act: -0.0000

Data Index: 769117 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.3914. Min Act: -0.0000

Data Index: 978966 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.3902. Min Act: -0.0000

Data Index: 828371 (C4 (Web Text))

Max Activating Token Index: 481

Text #6

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.3614. Min Act: -0.0000

Data Index: 1189530 (C4 (Web Text))

Max Activating Token Index: 776

Text #7

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.3496. Min Act: -0.0000

Data Index: 589510 (C4 (Web Text))

Max Activating Token Index: 835

Text #8

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.3729. Min Act: -0.0000

Data Index: 147079 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.3354. Min Act: -0.0000

Data Index: 32011 (C4 (Web Text))

Max Activating Token Index: 653

Text #10

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.3387. Min Act: -0.0000

Data Index: 634356 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.2999. Min Act: -0.0000

Data Index: 476853 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.2938. Min Act: -0.0000

Data Index: 1093891 (C4 (Web Text))

Max Activating Token Index: 188

Text #13

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.3248. Min Act: -0.0000

Data Index: 238290 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.2879. Min Act: -0.0000

Data Index: 707591 (C4 (Web Text))

Max Activating Token Index: 788

Text #15

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.3046. Min Act: -0.0000

Data Index: 765226 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.2549. Min Act: -0.0000

Data Index: 444409 (C4 (Web Text))

Max Activating Token Index: 802

Text #17

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.2634. Min Act: -0.0000

Data Index: 609008 (C4 (Web Text))

Max Activating Token Index: 202

Text #18

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.2662. Min Act: -0.0000

Data Index: 95406 (C4 (Web Text))

Max Activating Token Index: 973

Text #19

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.2514. Min Act: -0.0000

Data Index: 610671 (C4 (Web Text))

Max Activating Token Index: 802