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

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

Neuron 2631 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: 0.8574. Min Range: -0.8574

Max Act: 0.8574. Min Act: -0.0000

Data Index: 1432755 (Python Code)

Max Activating Token Index: 697

Text #1

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.7126. Min Act: -0.0000

Data Index: 1517461 (Python Code)

Max Activating Token Index: 952

Text #2

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.6155. Min Act: -0.0000

Data Index: 671789 (C4 (Web Text))

Max Activating Token Index: 604

Text #3

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.5525. Min Act: -0.0000

Data Index: 909611 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.5666. Min Act: -0.0000

Data Index: 1175753 (C4 (Web Text))

Max Activating Token Index: 491

Text #5

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.5366. Min Act: -0.0000

Data Index: 65425 (C4 (Web Text))

Max Activating Token Index: 660

Text #6

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.5693. Min Act: -0.0000

Data Index: 699174 (C4 (Web Text))

Max Activating Token Index: 348

Text #7

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.5516. Min Act: -0.0000

Data Index: 1498293 (Python Code)

Max Activating Token Index: 515

Text #8

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.5021. Min Act: -0.0000

Data Index: 1367666 (Python Code)

Max Activating Token Index: 518

Text #9

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.6095. Min Act: -0.0000

Data Index: 220036 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.5435. Min Act: -0.0000

Data Index: 1445699 (Python Code)

Max Activating Token Index: 446

Text #11

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.4749. Min Act: -0.0000

Data Index: 1515177 (Python Code)

Max Activating Token Index: 999

Text #12

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.5117. Min Act: -0.0000

Data Index: 1407637 (Python Code)

Max Activating Token Index: 634

Text #13

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.4814. Min Act: -0.0000

Data Index: 1596962 (Python Code)

Max Activating Token Index: 1009

Text #14

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.4811. Min Act: -0.0000

Data Index: 1385535 (Python Code)

Max Activating Token Index: 264

Text #15

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.5379. Min Act: -0.0000

Data Index: 1451396 (Python Code)

Max Activating Token Index: 701

Text #16

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.5183. Min Act: -0.0000

Data Index: 511820 (C4 (Web Text))

Max Activating Token Index: 313

Text #17

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.4847. Min Act: -0.0000

Data Index: 1377370 (Python Code)

Max Activating Token Index: 167

Text #18

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.4444. Min Act: -0.0000

Data Index: 244061 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.4610. Min Act: -0.0000

Data Index: 1575800 (Python Code)

Max Activating Token Index: 913