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

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

Neuron 2417 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0950. Min Range: -1.0950

Max Act: 1.0950. Min Act: -0.0000

Data Index: 296576 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 1.0950. Min Range: -1.0950

Max Act: 0.9852. Min Act: -0.0000

Data Index: 1593364 (Python Code)

Max Activating Token Index: 100

Text #2

Max Range: 1.0950. Min Range: -1.0950

Max Act: 0.8962. Min Act: -0.0000

Data Index: 1466682 (Python Code)

Max Activating Token Index: 56

Text #3

Max Range: 1.0950. Min Range: -1.0950

Max Act: 0.9047. Min Act: -0.0000

Data Index: 169036 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 1.0950. Min Range: -1.0950

Max Act: 0.8950. Min Act: -0.0000

Data Index: 1574705 (Python Code)

Max Activating Token Index: 253

Text #5

Max Range: 1.0950. Min Range: -1.0950

Max Act: 0.8181. Min Act: -0.0000

Data Index: 1424437 (Python Code)

Max Activating Token Index: 685

Text #6

Max Range: 1.0950. Min Range: -1.0950

Max Act: 0.7827. Min Act: 0.0000

Data Index: 1511481 (Python Code)

Max Activating Token Index: 126

Text #7

Max Range: 1.0950. Min Range: -1.0950

Max Act: 0.7383. Min Act: -0.0000

Data Index: 146415 (C4 (Web Text))

Max Activating Token Index: 776

Text #8

Max Range: 1.0950. Min Range: -1.0950

Max Act: 0.7390. Min Act: -0.0000

Data Index: 587230 (C4 (Web Text))

Max Activating Token Index: 406

Text #9

Max Range: 1.0950. Min Range: -1.0950

Max Act: 0.7102. Min Act: -0.0000

Data Index: 1494374 (Python Code)

Max Activating Token Index: 285

Text #10

Max Range: 1.0950. Min Range: -1.0950

Max Act: 0.7726. Min Act: -0.0000

Data Index: 1630305 (Python Code)

Max Activating Token Index: 38

Text #11

Max Range: 1.0950. Min Range: -1.0950

Max Act: 0.7455. Min Act: -0.0000

Data Index: 135073 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 1.0950. Min Range: -1.0950

Max Act: 0.7508. Min Act: -0.0000

Data Index: 1439356 (Python Code)

Max Activating Token Index: 209

Text #13

Max Range: 1.0950. Min Range: -1.0950

Max Act: 0.6864. Min Act: -0.0000

Data Index: 207559 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 1.0950. Min Range: -1.0950

Max Act: 0.7699. Min Act: -0.0000

Data Index: 480319 (C4 (Web Text))

Max Activating Token Index: 881

Text #15

Max Range: 1.0950. Min Range: -1.0950

Max Act: 0.7651. Min Act: -0.0000

Data Index: 1536242 (Python Code)

Max Activating Token Index: 1018

Text #16

Max Range: 1.0950. Min Range: -1.0950

Max Act: 0.7376. Min Act: -0.0000

Data Index: 873683 (C4 (Web Text))

Max Activating Token Index: 897

Text #17

Max Range: 1.0950. Min Range: -1.0950

Max Act: 0.7804. Min Act: -0.0000

Data Index: 1599584 (Python Code)

Max Activating Token Index: 54

Text #18

Max Range: 1.0950. Min Range: -1.0950

Max Act: 0.7552. Min Act: -0.0000

Data Index: 1041487 (C4 (Web Text))

Max Activating Token Index: 293

Text #19

Max Range: 1.0950. Min Range: -1.0950

Max Act: 0.6865. Min Act: -0.0000

Data Index: 1389894 (Python Code)

Max Activating Token Index: 517