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

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

Neuron 4858 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0839. Min Range: -2.0839

Max Act: 1.9968. Min Act: -0.0000

Data Index: 140471 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 2.0839. Min Range: -2.0839

Max Act: 2.0839. Min Act: -0.0000

Data Index: 196766 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 2.0839. Min Range: -2.0839

Max Act: 1.9250. Min Act: -0.0000

Data Index: 1234358 (C4 (Web Text))

Max Activating Token Index: 350

Text #3

Max Range: 2.0839. Min Range: -2.0839

Max Act: 1.9049. Min Act: -0.0000

Data Index: 793953 (C4 (Web Text))

Max Activating Token Index: 631

Text #4

Max Range: 2.0839. Min Range: -2.0839

Max Act: 1.7931. Min Act: -0.0000

Data Index: 869711 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 2.0839. Min Range: -2.0839

Max Act: 1.7834. Min Act: -0.0000

Data Index: 763427 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 2.0839. Min Range: -2.0839

Max Act: 1.7846. Min Act: -0.0000

Data Index: 1241417 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 2.0839. Min Range: -2.0839

Max Act: 1.7852. Min Act: -0.0000

Data Index: 1020210 (C4 (Web Text))

Max Activating Token Index: 843

Text #8

Max Range: 2.0839. Min Range: -2.0839

Max Act: 1.8705. Min Act: -0.0000

Data Index: 1011186 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 2.0839. Min Range: -2.0839

Max Act: 1.6897. Min Act: -0.0000

Data Index: 971120 (C4 (Web Text))

Max Activating Token Index: 869

Text #10

Max Range: 2.0839. Min Range: -2.0839

Max Act: 1.8453. Min Act: -0.0000

Data Index: 332727 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 2.0839. Min Range: -2.0839

Max Act: 1.7149. Min Act: -0.0000

Data Index: 936892 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 2.0839. Min Range: -2.0839

Max Act: 1.6817. Min Act: -0.0000

Data Index: 1071165 (C4 (Web Text))

Max Activating Token Index: 539

Text #13

Max Range: 2.0839. Min Range: -2.0839

Max Act: 1.6138. Min Act: -0.0000

Data Index: 687845 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 2.0839. Min Range: -2.0839

Max Act: 1.6394. Min Act: -0.0000

Data Index: 792070 (C4 (Web Text))

Max Activating Token Index: 473

Text #15

Max Range: 2.0839. Min Range: -2.0839

Max Act: 1.5760. Min Act: -0.0000

Data Index: 1341742 (C4 (Web Text))

Max Activating Token Index: 1007

Text #16

Max Range: 2.0839. Min Range: -2.0839

Max Act: 1.5504. Min Act: -0.0000

Data Index: 842746 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 2.0839. Min Range: -2.0839

Max Act: 1.5801. Min Act: -0.0000

Data Index: 121834 (C4 (Web Text))

Max Activating Token Index: 275

Text #18

Max Range: 2.0839. Min Range: -2.0839

Max Act: 1.4417. Min Act: -0.0000

Data Index: 621137 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 2.0839. Min Range: -2.0839

Max Act: 1.4336. Min Act: -0.0000

Data Index: 880683 (C4 (Web Text))

Max Activating Token Index: 46