Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3301 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.9768. Min Act: -0.0000

Data Index: 1005858 (C4 (Web Text))

Max Activating Token Index: 492

Text #1

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.8328. Min Act: 0.0000

Data Index: 45717 (C4 (Web Text))

Max Activating Token Index: 369

Text #2

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.8550. Min Act: -0.0000

Data Index: 182614 (C4 (Web Text))

Max Activating Token Index: 700

Text #3

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.8509. Min Act: -0.0000

Data Index: 947611 (C4 (Web Text))

Max Activating Token Index: 22

Text #4

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.8488. Min Act: -0.0000

Data Index: 1194097 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.8225. Min Act: -0.0000

Data Index: 1393026 (Python Code)

Max Activating Token Index: 785

Text #6

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.8630. Min Act: -0.0000

Data Index: 653954 (C4 (Web Text))

Max Activating Token Index: 713

Text #7

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.7955. Min Act: -0.0000

Data Index: 335027 (C4 (Web Text))

Max Activating Token Index: 280

Text #8

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.7487. Min Act: -0.0000

Data Index: 1128389 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.7354. Min Act: -0.0000

Data Index: 1271408 (C4 (Web Text))

Max Activating Token Index: 965

Text #10

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.6947. Min Act: -0.0000

Data Index: 335812 (C4 (Web Text))

Max Activating Token Index: 865

Text #11

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.7513. Min Act: -0.0000

Data Index: 1390922 (Python Code)

Max Activating Token Index: 481

Text #12

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.6782. Min Act: -0.0000

Data Index: 34504 (C4 (Web Text))

Max Activating Token Index: 642

Text #13

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.7738. Min Act: -0.0000

Data Index: 126987 (C4 (Web Text))

Max Activating Token Index: 690

Text #14

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.7406. Min Act: -0.0000

Data Index: 71455 (C4 (Web Text))

Max Activating Token Index: 520

Text #15

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.7736. Min Act: -0.0000

Data Index: 1548797 (Python Code)

Max Activating Token Index: 995

Text #16

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.7213. Min Act: -0.0000

Data Index: 156335 (C4 (Web Text))

Max Activating Token Index: 606

Text #17

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.6967. Min Act: -0.0000

Data Index: 1073410 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.7296. Min Act: -0.0000

Data Index: 1472787 (Python Code)

Max Activating Token Index: 159

Text #19

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.6875. Min Act: -0.0000

Data Index: 565024 (C4 (Web Text))

Max Activating Token Index: 441