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

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

Neuron 1470 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6563. Min Range: -0.6563

Max Act: 0.6563. Min Act: -0.0000

Data Index: 908321 (C4 (Web Text))

Max Activating Token Index: 457

Text #1

Max Range: 0.6563. Min Range: -0.6563

Max Act: 0.6486. Min Act: -0.0000

Data Index: 97388 (C4 (Web Text))

Max Activating Token Index: 790

Text #2

Max Range: 0.6563. Min Range: -0.6563

Max Act: 0.5985. Min Act: -0.0000

Data Index: 505296 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 0.6563. Min Range: -0.6563

Max Act: 0.6129. Min Act: -0.0000

Data Index: 47287 (C4 (Web Text))

Max Activating Token Index: 404

Text #4

Max Range: 0.6563. Min Range: -0.6563

Max Act: 0.5755. Min Act: -0.0000

Data Index: 792657 (C4 (Web Text))

Max Activating Token Index: 303

Text #5

Max Range: 0.6563. Min Range: -0.6563

Max Act: 0.5556. Min Act: -0.0000

Data Index: 992911 (C4 (Web Text))

Max Activating Token Index: 595

Text #6

Max Range: 0.6563. Min Range: -0.6563

Max Act: 0.6064. Min Act: -0.0000

Data Index: 704324 (C4 (Web Text))

Max Activating Token Index: 568

Text #7

Max Range: 0.6563. Min Range: -0.6563

Max Act: 0.5771. Min Act: -0.0000

Data Index: 143865 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 0.6563. Min Range: -0.6563

Max Act: 0.5295. Min Act: -0.0000

Data Index: 82854 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 0.6563. Min Range: -0.6563

Max Act: 0.5319. Min Act: -0.0000

Data Index: 768635 (C4 (Web Text))

Max Activating Token Index: 615

Text #10

Max Range: 0.6563. Min Range: -0.6563

Max Act: 0.5390. Min Act: -0.0000

Data Index: 1270397 (C4 (Web Text))

Max Activating Token Index: 430

Text #11

Max Range: 0.6563. Min Range: -0.6563

Max Act: 0.5073. Min Act: -0.0000

Data Index: 238764 (C4 (Web Text))

Max Activating Token Index: 202

Text #12

Max Range: 0.6563. Min Range: -0.6563

Max Act: 0.4896. Min Act: -0.0000

Data Index: 44746 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 0.6563. Min Range: -0.6563

Max Act: 0.5374. Min Act: -0.0000

Data Index: 449846 (C4 (Web Text))

Max Activating Token Index: 369

Text #14

Max Range: 0.6563. Min Range: -0.6563

Max Act: 0.5162. Min Act: -0.0000

Data Index: 722607 (C4 (Web Text))

Max Activating Token Index: 357

Text #15

Max Range: 0.6563. Min Range: -0.6563

Max Act: 0.5114. Min Act: -0.0000

Data Index: 892319 (C4 (Web Text))

Max Activating Token Index: 959

Text #16

Max Range: 0.6563. Min Range: -0.6563

Max Act: 0.4974. Min Act: -0.0000

Data Index: 668658 (C4 (Web Text))

Max Activating Token Index: 360

Text #17

Max Range: 0.6563. Min Range: -0.6563

Max Act: 0.4649. Min Act: -0.0000

Data Index: 1328685 (C4 (Web Text))

Max Activating Token Index: 1021

Text #18

Max Range: 0.6563. Min Range: -0.6563

Max Act: 0.4651. Min Act: -0.0000

Data Index: 422653 (C4 (Web Text))

Max Activating Token Index: 909

Text #19

Max Range: 0.6563. Min Range: -0.6563

Max Act: 0.4654. Min Act: -0.0000

Data Index: 1199277 (C4 (Web Text))

Max Activating Token Index: 950