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

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

Neuron 4019 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: 0.6800. Min Range: -0.6800

Max Act: 0.6800. Min Act: -0.0000

Data Index: 730210 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 0.6800. Min Range: -0.6800

Max Act: 0.6760. Min Act: -0.0000

Data Index: 420340 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 0.6800. Min Range: -0.6800

Max Act: 0.6594. Min Act: -0.0000

Data Index: 249189 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 0.6800. Min Range: -0.6800

Max Act: 0.6077. Min Act: -0.0000

Data Index: 618248 (C4 (Web Text))

Max Activating Token Index: 731

Text #4

Max Range: 0.6800. Min Range: -0.6800

Max Act: 0.5482. Min Act: 0.0001

Data Index: 249959 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 0.6800. Min Range: -0.6800

Max Act: 0.5461. Min Act: -0.0000

Data Index: 690670 (C4 (Web Text))

Max Activating Token Index: 508

Text #6

Max Range: 0.6800. Min Range: -0.6800

Max Act: 0.4980. Min Act: -0.0000

Data Index: 614781 (C4 (Web Text))

Max Activating Token Index: 631

Text #7

Max Range: 0.6800. Min Range: -0.6800

Max Act: 0.4975. Min Act: -0.0000

Data Index: 351911 (C4 (Web Text))

Max Activating Token Index: 620

Text #8

Max Range: 0.6800. Min Range: -0.6800

Max Act: 0.4953. Min Act: 0.0000

Data Index: 978110 (C4 (Web Text))

Max Activating Token Index: 479

Text #9

Max Range: 0.6800. Min Range: -0.6800

Max Act: 0.4938. Min Act: -0.0000

Data Index: 750702 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 0.6800. Min Range: -0.6800

Max Act: 0.5195. Min Act: -0.0000

Data Index: 258664 (C4 (Web Text))

Max Activating Token Index: 257

Text #11

Max Range: 0.6800. Min Range: -0.6800

Max Act: 0.4914. Min Act: -0.0000

Data Index: 12319 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 0.6800. Min Range: -0.6800

Max Act: 0.4893. Min Act: -0.0000

Data Index: 1308551 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 0.6800. Min Range: -0.6800

Max Act: 0.4735. Min Act: -0.0000

Data Index: 1091286 (C4 (Web Text))

Max Activating Token Index: 882

Text #14

Max Range: 0.6800. Min Range: -0.6800

Max Act: 0.4846. Min Act: -0.0000

Data Index: 1294953 (C4 (Web Text))

Max Activating Token Index: 610

Text #15

Max Range: 0.6800. Min Range: -0.6800

Max Act: 0.4648. Min Act: -0.0000

Data Index: 723676 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 0.6800. Min Range: -0.6800

Max Act: 0.4534. Min Act: -0.0000

Data Index: 705233 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 0.6800. Min Range: -0.6800

Max Act: 0.4564. Min Act: -0.0000

Data Index: 846465 (C4 (Web Text))

Max Activating Token Index: 786

Text #18

Max Range: 0.6800. Min Range: -0.6800

Max Act: 0.4805. Min Act: -0.0000

Data Index: 217456 (C4 (Web Text))

Max Activating Token Index: 551

Text #19

Max Range: 0.6800. Min Range: -0.6800

Max Act: 0.4592. Min Act: -0.0000

Data Index: 631260 (C4 (Web Text))

Max Activating Token Index: 601