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

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

Neuron 1753 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: 2.5351. Min Range: -2.5351

Max Act: 2.5351. Min Act: -0.0000

Data Index: 1077635 (C4 (Web Text))

Max Activating Token Index: 641

Text #1

Max Range: 2.5351. Min Range: -2.5351

Max Act: 1.9714. Min Act: -0.0000

Data Index: 64495 (C4 (Web Text))

Max Activating Token Index: 879

Text #2

Max Range: 2.5351. Min Range: -2.5351

Max Act: 2.1105. Min Act: -0.0000

Data Index: 1270432 (C4 (Web Text))

Max Activating Token Index: 431

Text #3

Max Range: 2.5351. Min Range: -2.5351

Max Act: 2.0150. Min Act: -0.0000

Data Index: 307547 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 2.5351. Min Range: -2.5351

Max Act: 1.8057. Min Act: -0.0000

Data Index: 1169622 (C4 (Web Text))

Max Activating Token Index: 937

Text #5

Max Range: 2.5351. Min Range: -2.5351

Max Act: 1.9675. Min Act: -0.0000

Data Index: 1212649 (C4 (Web Text))

Max Activating Token Index: 629

Text #6

Max Range: 2.5351. Min Range: -2.5351

Max Act: 1.8081. Min Act: 0.0002

Data Index: 918463 (C4 (Web Text))

Max Activating Token Index: 553

Text #7

Max Range: 2.5351. Min Range: -2.5351

Max Act: 1.8062. Min Act: 0.0000

Data Index: 94331 (C4 (Web Text))

Max Activating Token Index: 225

Text #8

Max Range: 2.5351. Min Range: -2.5351

Max Act: 1.7143. Min Act: -0.0000

Data Index: 1123403 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 2.5351. Min Range: -2.5351

Max Act: 1.7521. Min Act: -0.0000

Data Index: 792969 (C4 (Web Text))

Max Activating Token Index: 872

Text #10

Max Range: 2.5351. Min Range: -2.5351

Max Act: 1.6537. Min Act: -0.0000

Data Index: 159883 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 2.5351. Min Range: -2.5351

Max Act: 1.6940. Min Act: -0.0000

Data Index: 357526 (C4 (Web Text))

Max Activating Token Index: 432

Text #12

Max Range: 2.5351. Min Range: -2.5351

Max Act: 1.5737. Min Act: -0.0000

Data Index: 724747 (C4 (Web Text))

Max Activating Token Index: 504

Text #13

Max Range: 2.5351. Min Range: -2.5351

Max Act: 1.7453. Min Act: 0.0001

Data Index: 705955 (C4 (Web Text))

Max Activating Token Index: 640

Text #14

Max Range: 2.5351. Min Range: -2.5351

Max Act: 1.5329. Min Act: -0.0000

Data Index: 1285829 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 2.5351. Min Range: -2.5351

Max Act: 1.5192. Min Act: -0.0000

Data Index: 202655 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 2.5351. Min Range: -2.5351

Max Act: 1.4986. Min Act: -0.0000

Data Index: 1308063 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 2.5351. Min Range: -2.5351

Max Act: 1.3527. Min Act: -0.0000

Data Index: 29973 (C4 (Web Text))

Max Activating Token Index: 940

Text #18

Max Range: 2.5351. Min Range: -2.5351

Max Act: 1.5080. Min Act: -0.0000

Data Index: 877750 (C4 (Web Text))

Max Activating Token Index: 668

Text #19

Max Range: 2.5351. Min Range: -2.5351

Max Act: 1.4762. Min Act: -0.0000

Data Index: 326097 (C4 (Web Text))

Max Activating Token Index: 79