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

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

Neuron 3288 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: 0.7455. Min Range: -0.7455

Max Act: 0.7455. Min Act: -0.0000

Data Index: 439595 (C4 (Web Text))

Max Activating Token Index: 516

Text #1

Max Range: 0.7455. Min Range: -0.7455

Max Act: 0.7065. Min Act: -0.0000

Data Index: 1150840 (C4 (Web Text))

Max Activating Token Index: 783

Text #2

Max Range: 0.7455. Min Range: -0.7455

Max Act: 0.6724. Min Act: -0.0000

Data Index: 583277 (C4 (Web Text))

Max Activating Token Index: 936

Text #3

Max Range: 0.7455. Min Range: -0.7455

Max Act: 0.5977. Min Act: -0.0000

Data Index: 1377054 (Python Code)

Max Activating Token Index: 297

Text #4

Max Range: 0.7455. Min Range: -0.7455

Max Act: 0.6129. Min Act: -0.0000

Data Index: 775389 (C4 (Web Text))

Max Activating Token Index: 898

Text #5

Max Range: 0.7455. Min Range: -0.7455

Max Act: 0.5993. Min Act: -0.0000

Data Index: 996266 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 0.7455. Min Range: -0.7455

Max Act: 0.5897. Min Act: -0.0000

Data Index: 1630424 (Python Code)

Max Activating Token Index: 565

Text #7

Max Range: 0.7455. Min Range: -0.7455

Max Act: 0.5808. Min Act: -0.0000

Data Index: 346199 (C4 (Web Text))

Max Activating Token Index: 777

Text #8

Max Range: 0.7455. Min Range: -0.7455

Max Act: 0.5990. Min Act: -0.0000

Data Index: 1491668 (Python Code)

Max Activating Token Index: 869

Text #9

Max Range: 0.7455. Min Range: -0.7455

Max Act: 0.5638. Min Act: -0.0000

Data Index: 1376980 (Python Code)

Max Activating Token Index: 539

Text #10

Max Range: 0.7455. Min Range: -0.7455

Max Act: 0.6247. Min Act: -0.0000

Data Index: 985751 (C4 (Web Text))

Max Activating Token Index: 659

Text #11

Max Range: 0.7455. Min Range: -0.7455

Max Act: 0.4784. Min Act: -0.0000

Data Index: 830320 (C4 (Web Text))

Max Activating Token Index: 223

Text #12

Max Range: 0.7455. Min Range: -0.7455

Max Act: 0.5250. Min Act: -0.0000

Data Index: 988750 (C4 (Web Text))

Max Activating Token Index: 1014

Text #13

Max Range: 0.7455. Min Range: -0.7455

Max Act: 0.6161. Min Act: -0.0000

Data Index: 1153323 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 0.7455. Min Range: -0.7455

Max Act: 0.5975. Min Act: -0.0000

Data Index: 201715 (C4 (Web Text))

Max Activating Token Index: 738

Text #15

Max Range: 0.7455. Min Range: -0.7455

Max Act: 0.5693. Min Act: -0.0000

Data Index: 1063295 (C4 (Web Text))

Max Activating Token Index: 1004

Text #16

Max Range: 0.7455. Min Range: -0.7455

Max Act: 0.5694. Min Act: -0.0000

Data Index: 264919 (C4 (Web Text))

Max Activating Token Index: 321

Text #17

Max Range: 0.7455. Min Range: -0.7455

Max Act: 0.5520. Min Act: -0.0000

Data Index: 1025172 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 0.7455. Min Range: -0.7455

Max Act: 0.5803. Min Act: -0.0000

Data Index: 49091 (C4 (Web Text))

Max Activating Token Index: 592

Text #19

Max Range: 0.7455. Min Range: -0.7455

Max Act: 0.5574. Min Act: -0.0000

Data Index: 1590602 (Python Code)

Max Activating Token Index: 477