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

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

Neuron 1253 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1768. Min Range: -1.1768

Max Act: 1.1768. Min Act: -0.0000

Data Index: 420975 (C4 (Web Text))

Max Activating Token Index: 866

Text #1

Max Range: 1.1768. Min Range: -1.1768

Max Act: 1.0005. Min Act: -0.0000

Data Index: 729438 (C4 (Web Text))

Max Activating Token Index: 462

Text #2

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.9246. Min Act: -0.0000

Data Index: 711173 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.8894. Min Act: -0.0000

Data Index: 760978 (C4 (Web Text))

Max Activating Token Index: 254

Text #4

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.8844. Min Act: -0.0000

Data Index: 33850 (C4 (Web Text))

Max Activating Token Index: 618

Text #5

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.8629. Min Act: -0.0000

Data Index: 989085 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.8244. Min Act: -0.0000

Data Index: 109468 (C4 (Web Text))

Max Activating Token Index: 936

Text #7

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.8057. Min Act: -0.0000

Data Index: 401464 (C4 (Web Text))

Max Activating Token Index: 329

Text #8

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.8429. Min Act: -0.0000

Data Index: 820470 (C4 (Web Text))

Max Activating Token Index: 344

Text #9

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.8068. Min Act: -0.0000

Data Index: 176400 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.7773. Min Act: -0.0000

Data Index: 543241 (C4 (Web Text))

Max Activating Token Index: 188

Text #11

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.8044. Min Act: -0.0000

Data Index: 679479 (C4 (Web Text))

Max Activating Token Index: 980

Text #12

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.7834. Min Act: -0.0000

Data Index: 1435 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.7741. Min Act: -0.0000

Data Index: 1166304 (C4 (Web Text))

Max Activating Token Index: 867

Text #14

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.7508. Min Act: -0.0000

Data Index: 578986 (C4 (Web Text))

Max Activating Token Index: 941

Text #15

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.7040. Min Act: -0.0000

Data Index: 149088 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.6780. Min Act: -0.0000

Data Index: 56304 (C4 (Web Text))

Max Activating Token Index: 274

Text #17

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.6974. Min Act: -0.0000

Data Index: 265158 (C4 (Web Text))

Max Activating Token Index: 786

Text #18

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.7376. Min Act: -0.0000

Data Index: 967551 (C4 (Web Text))

Max Activating Token Index: 873

Text #19

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.7076. Min Act: -0.0000

Data Index: 156138 (C4 (Web Text))

Max Activating Token Index: 906