Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2410 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.4392. Min Range: -2.4392

Max Act: 2.4392. Min Act: -0.0000

Data Index: 886059 (C4 (Web Text))

Max Activating Token Index: 558

Text #1

Max Range: 2.4392. Min Range: -2.4392

Max Act: 1.2888. Min Act: -0.0000

Data Index: 258167 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 2.4392. Min Range: -2.4392

Max Act: 1.1930. Min Act: -0.0000

Data Index: 302421 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 2.4392. Min Range: -2.4392

Max Act: 1.0420. Min Act: -0.0000

Data Index: 1054670 (C4 (Web Text))

Max Activating Token Index: 356

Text #4

Max Range: 2.4392. Min Range: -2.4392

Max Act: 1.1015. Min Act: -0.0000

Data Index: 275454 (C4 (Web Text))

Max Activating Token Index: 544

Text #5

Max Range: 2.4392. Min Range: -2.4392

Max Act: 0.9068. Min Act: -0.0000

Data Index: 691176 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 2.4392. Min Range: -2.4392

Max Act: 0.8978. Min Act: -0.0000

Data Index: 1327838 (C4 (Web Text))

Max Activating Token Index: 930

Text #7

Max Range: 2.4392. Min Range: -2.4392

Max Act: 0.8147. Min Act: -0.0000

Data Index: 668274 (C4 (Web Text))

Max Activating Token Index: 729

Text #8

Max Range: 2.4392. Min Range: -2.4392

Max Act: 0.8471. Min Act: -0.0000

Data Index: 1122950 (C4 (Web Text))

Max Activating Token Index: 318

Text #9

Max Range: 2.4392. Min Range: -2.4392

Max Act: 0.7834. Min Act: -0.0000

Data Index: 492725 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 2.4392. Min Range: -2.4392

Max Act: 0.6635. Min Act: -0.0000

Data Index: 765863 (C4 (Web Text))

Max Activating Token Index: 459

Text #11

Max Range: 2.4392. Min Range: -2.4392

Max Act: 0.6448. Min Act: -0.0000

Data Index: 1440286 (Python Code)

Max Activating Token Index: 105

Text #12

Max Range: 2.4392. Min Range: -2.4392

Max Act: 0.6043. Min Act: -0.0000

Data Index: 886821 (C4 (Web Text))

Max Activating Token Index: 758

Text #13

Max Range: 2.4392. Min Range: -2.4392

Max Act: 0.9072. Min Act: -0.0000

Data Index: 1304631 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 2.4392. Min Range: -2.4392

Max Act: 0.6267. Min Act: -0.0000

Data Index: 807397 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 2.4392. Min Range: -2.4392

Max Act: 0.6097. Min Act: -0.0000

Data Index: 243237 (C4 (Web Text))

Max Activating Token Index: 981

Text #16

Max Range: 2.4392. Min Range: -2.4392

Max Act: 0.5913. Min Act: -0.0000

Data Index: 1011149 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 2.4392. Min Range: -2.4392

Max Act: 0.4946. Min Act: -0.0000

Data Index: 1549106 (Python Code)

Max Activating Token Index: 141

Text #18

Max Range: 2.4392. Min Range: -2.4392

Max Act: 0.5825. Min Act: -0.0000

Data Index: 982657 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 2.4392. Min Range: -2.4392

Max Act: 0.5804. Min Act: -0.0000

Data Index: 1561389 (Python Code)

Max Activating Token Index: 290