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

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

Neuron 3543 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.9414. Min Act: -0.0000

Data Index: 123633 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.8986. Min Act: -0.0001

Data Index: 984363 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.8949. Min Act: -0.0001

Data Index: 635566 (C4 (Web Text))

Max Activating Token Index: 505

Text #3

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.8815. Min Act: -0.0001

Data Index: 699856 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.8364. Min Act: -0.0000

Data Index: 406856 (C4 (Web Text))

Max Activating Token Index: 810

Text #5

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.8327. Min Act: -0.0000

Data Index: 986351 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.8521. Min Act: -0.0000

Data Index: 500598 (C4 (Web Text))

Max Activating Token Index: 971

Text #7

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.8810. Min Act: -0.0000

Data Index: 1262663 (C4 (Web Text))

Max Activating Token Index: 668

Text #8

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.7629. Min Act: -0.0001

Data Index: 1093014 (C4 (Web Text))

Max Activating Token Index: 872

Text #9

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.8359. Min Act: -0.0000

Data Index: 461139 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.8243. Min Act: -0.0000

Data Index: 1129252 (C4 (Web Text))

Max Activating Token Index: 892

Text #11

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.7953. Min Act: -0.0000

Data Index: 660569 (C4 (Web Text))

Max Activating Token Index: 940

Text #12

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.8197. Min Act: -0.0000

Data Index: 374377 (C4 (Web Text))

Max Activating Token Index: 979

Text #13

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.7915. Min Act: -0.0000

Data Index: 1356266 (C4 (Web Text))

Max Activating Token Index: 699

Text #14

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.7877. Min Act: -0.0000

Data Index: 14108 (C4 (Web Text))

Max Activating Token Index: 764

Text #15

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.7849. Min Act: -0.0001

Data Index: 1147954 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.7747. Min Act: -0.0000

Data Index: 202355 (C4 (Web Text))

Max Activating Token Index: 220

Text #17

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.7970. Min Act: -0.0000

Data Index: 693484 (C4 (Web Text))

Max Activating Token Index: 379

Text #18

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.7973. Min Act: -0.0000

Data Index: 531695 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.7941. Min Act: -0.0000

Data Index: 789152 (C4 (Web Text))

Max Activating Token Index: 11