Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3411 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8454. Min Range: -0.8454

Max Act: 0.8454. Min Act: -0.0002

Data Index: 437883 (C4 (Web Text))

Max Activating Token Index: 613

Text #1

Max Range: 0.8454. Min Range: -0.8454

Max Act: 0.8245. Min Act: -0.0002

Data Index: 347826 (C4 (Web Text))

Max Activating Token Index: 749

Text #2

Max Range: 0.8454. Min Range: -0.8454

Max Act: 0.7947. Min Act: -0.0001

Data Index: 302500 (C4 (Web Text))

Max Activating Token Index: 701

Text #3

Max Range: 0.8454. Min Range: -0.8454

Max Act: 0.8096. Min Act: -0.0002

Data Index: 1085242 (C4 (Web Text))

Max Activating Token Index: 640

Text #4

Max Range: 0.8454. Min Range: -0.8454

Max Act: 0.7848. Min Act: -0.0001

Data Index: 852036 (C4 (Web Text))

Max Activating Token Index: 629

Text #5

Max Range: 0.8454. Min Range: -0.8454

Max Act: 0.7829. Min Act: -0.0002

Data Index: 1233316 (C4 (Web Text))

Max Activating Token Index: 472

Text #6

Max Range: 0.8454. Min Range: -0.8454

Max Act: 0.8065. Min Act: -0.0002

Data Index: 346029 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 0.8454. Min Range: -0.8454

Max Act: 0.7340. Min Act: -0.0001

Data Index: 225506 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 0.8454. Min Range: -0.8454

Max Act: 0.7534. Min Act: -0.0002

Data Index: 232197 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 0.8454. Min Range: -0.8454

Max Act: 0.7512. Min Act: -0.0001

Data Index: 478332 (C4 (Web Text))

Max Activating Token Index: 922

Text #10

Max Range: 0.8454. Min Range: -0.8454

Max Act: 0.7727. Min Act: -0.0001

Data Index: 830916 (C4 (Web Text))

Max Activating Token Index: 464

Text #11

Max Range: 0.8454. Min Range: -0.8454

Max Act: 0.7505. Min Act: -0.0001

Data Index: 1566059 (Python Code)

Max Activating Token Index: 255

Text #12

Max Range: 0.8454. Min Range: -0.8454

Max Act: 0.7698. Min Act: -0.0002

Data Index: 1080372 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 0.8454. Min Range: -0.8454

Max Act: 0.7686. Min Act: -0.0002

Data Index: 734674 (C4 (Web Text))

Max Activating Token Index: 457

Text #14

Max Range: 0.8454. Min Range: -0.8454

Max Act: 0.7662. Min Act: -0.0002

Data Index: 678055 (C4 (Web Text))

Max Activating Token Index: 341

Text #15

Max Range: 0.8454. Min Range: -0.8454

Max Act: 0.7441. Min Act: -0.0001

Data Index: 25081 (C4 (Web Text))

Max Activating Token Index: 806

Text #16

Max Range: 0.8454. Min Range: -0.8454

Max Act: 0.7325. Min Act: -0.0002

Data Index: 610808 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 0.8454. Min Range: -0.8454

Max Act: 0.7545. Min Act: -0.0002

Data Index: 1063915 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 0.8454. Min Range: -0.8454

Max Act: 0.7540. Min Act: -0.0002

Data Index: 968086 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 0.8454. Min Range: -0.8454

Max Act: 0.7481. Min Act: -0.0001

Data Index: 196588 (C4 (Web Text))

Max Activating Token Index: 334