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

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

Neuron 3009 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: 0.6893. Min Range: -0.6893

Max Act: 0.6893. Min Act: -0.0000

Data Index: 486073 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.6280. Min Act: -0.0000

Data Index: 49627 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.6123. Min Act: -0.0000

Data Index: 141301 (C4 (Web Text))

Max Activating Token Index: 370

Text #3

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.5898. Min Act: -0.0000

Data Index: 106761 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.5804. Min Act: -0.0000

Data Index: 778216 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.5793. Min Act: -0.0000

Data Index: 510501 (C4 (Web Text))

Max Activating Token Index: 55

Text #6

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.5638. Min Act: -0.0000

Data Index: 890209 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.5895. Min Act: -0.0000

Data Index: 1618368 (Python Code)

Max Activating Token Index: 793

Text #8

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.5469. Min Act: -0.0000

Data Index: 984078 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.5375. Min Act: -0.0000

Data Index: 370942 (C4 (Web Text))

Max Activating Token Index: 264

Text #10

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.4818. Min Act: -0.0000

Data Index: 1393362 (Python Code)

Max Activating Token Index: 449

Text #11

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.4802. Min Act: -0.0000

Data Index: 619652 (C4 (Web Text))

Max Activating Token Index: 280

Text #12

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.4747. Min Act: -0.0000

Data Index: 753894 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.4902. Min Act: -0.0000

Data Index: 116701 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.4732. Min Act: -0.0000

Data Index: 848668 (C4 (Web Text))

Max Activating Token Index: 259

Text #15

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.5000. Min Act: 0.0000

Data Index: 1302220 (C4 (Web Text))

Max Activating Token Index: 467

Text #16

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.4785. Min Act: -0.0000

Data Index: 524042 (C4 (Web Text))

Max Activating Token Index: 838

Text #17

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.4784. Min Act: -0.0000

Data Index: 347778 (C4 (Web Text))

Max Activating Token Index: 261

Text #18

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.4673. Min Act: -0.0000

Data Index: 913238 (C4 (Web Text))

Max Activating Token Index: 974

Text #19

Max Range: 0.6893. Min Range: -0.6893

Max Act: 0.4648. Min Act: 0.0000

Data Index: 1302776 (C4 (Web Text))

Max Activating Token Index: 689