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

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

Neuron 3537 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1768. Min Range: -1.1768

Max Act: 1.1729. Min Act: -0.0000

Data Index: 856649 (C4 (Web Text))

Max Activating Token Index: 172

Text #1

Max Range: 1.1768. Min Range: -1.1768

Max Act: 1.1768. Min Act: -0.0000

Data Index: 419286 (C4 (Web Text))

Max Activating Token Index: 846

Text #2

Max Range: 1.1768. Min Range: -1.1768

Max Act: 1.0002. Min Act: -0.0001

Data Index: 358998 (C4 (Web Text))

Max Activating Token Index: 150

Text #3

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.9817. Min Act: -0.0001

Data Index: 707739 (C4 (Web Text))

Max Activating Token Index: 629

Text #4

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.9789. Min Act: -0.0000

Data Index: 415166 (C4 (Web Text))

Max Activating Token Index: 599

Text #5

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.9258. Min Act: -0.0001

Data Index: 649916 (C4 (Web Text))

Max Activating Token Index: 735

Text #6

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.8709. Min Act: -0.0000

Data Index: 670894 (C4 (Web Text))

Max Activating Token Index: 227

Text #7

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.9015. Min Act: -0.0001

Data Index: 191478 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.8661. Min Act: -0.0000

Data Index: 1041260 (C4 (Web Text))

Max Activating Token Index: 779

Text #9

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.8341. Min Act: -0.0000

Data Index: 935788 (C4 (Web Text))

Max Activating Token Index: 377

Text #10

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.9178. Min Act: -0.0000

Data Index: 813969 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.8512. Min Act: -0.0000

Data Index: 1080564 (C4 (Web Text))

Max Activating Token Index: 717

Text #12

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.8944. Min Act: -0.0000

Data Index: 334297 (C4 (Web Text))

Max Activating Token Index: 711

Text #13

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.9099. Min Act: -0.0001

Data Index: 680159 (C4 (Web Text))

Max Activating Token Index: 909

Text #14

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.7901. Min Act: -0.0001

Data Index: 25336 (C4 (Web Text))

Max Activating Token Index: 316

Text #15

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.8244. Min Act: -0.0001

Data Index: 45041 (C4 (Web Text))

Max Activating Token Index: 796

Text #16

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.8594. Min Act: -0.0001

Data Index: 325190 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.8494. Min Act: -0.0000

Data Index: 410188 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.8188. Min Act: -0.0001

Data Index: 1066785 (C4 (Web Text))

Max Activating Token Index: 542

Text #19

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.8393. Min Act: -0.0000

Data Index: 1358071 (C4 (Web Text))

Max Activating Token Index: 355