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

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

Neuron 5171 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: 1.6022. Min Range: -1.6022

Max Act: 1.6022. Min Act: -0.0000

Data Index: 660486 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 1.6022. Min Range: -1.6022

Max Act: 1.2722. Min Act: -0.0000

Data Index: 946781 (C4 (Web Text))

Max Activating Token Index: 194

Text #2

Max Range: 1.6022. Min Range: -1.6022

Max Act: 1.2261. Min Act: -0.0000

Data Index: 688540 (C4 (Web Text))

Max Activating Token Index: 444

Text #3

Max Range: 1.6022. Min Range: -1.6022

Max Act: 1.2594. Min Act: -0.0000

Data Index: 1459898 (Python Code)

Max Activating Token Index: 964

Text #4

Max Range: 1.6022. Min Range: -1.6022

Max Act: 1.2100. Min Act: -0.0000

Data Index: 829560 (C4 (Web Text))

Max Activating Token Index: 566

Text #5

Max Range: 1.6022. Min Range: -1.6022

Max Act: 1.2032. Min Act: -0.0000

Data Index: 1328102 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 1.6022. Min Range: -1.6022

Max Act: 1.2038. Min Act: -0.0000

Data Index: 1159961 (C4 (Web Text))

Max Activating Token Index: 399

Text #7

Max Range: 1.6022. Min Range: -1.6022

Max Act: 1.2310. Min Act: -0.0000

Data Index: 1569707 (Python Code)

Max Activating Token Index: 333

Text #8

Max Range: 1.6022. Min Range: -1.6022

Max Act: 1.1879. Min Act: -0.0000

Data Index: 537807 (C4 (Web Text))

Max Activating Token Index: 946

Text #9

Max Range: 1.6022. Min Range: -1.6022

Max Act: 1.1601. Min Act: -0.0000

Data Index: 57731 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 1.6022. Min Range: -1.6022

Max Act: 1.1227. Min Act: -0.0000

Data Index: 1640741 (Python Code)

Max Activating Token Index: 444

Text #11

Max Range: 1.6022. Min Range: -1.6022

Max Act: 1.0314. Min Act: 0.0001

Data Index: 154018 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 1.6022. Min Range: -1.6022

Max Act: 1.1304. Min Act: -0.0000

Data Index: 1554362 (Python Code)

Max Activating Token Index: 800

Text #13

Max Range: 1.6022. Min Range: -1.6022

Max Act: 1.1573. Min Act: 0.0000

Data Index: 945238 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 1.6022. Min Range: -1.6022

Max Act: 1.1340. Min Act: -0.0000

Data Index: 230215 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 1.6022. Min Range: -1.6022

Max Act: 1.1650. Min Act: -0.0000

Data Index: 1497860 (Python Code)

Max Activating Token Index: 242

Text #16

Max Range: 1.6022. Min Range: -1.6022

Max Act: 1.1667. Min Act: -0.0000

Data Index: 1582226 (Python Code)

Max Activating Token Index: 695

Text #17

Max Range: 1.6022. Min Range: -1.6022

Max Act: 1.0895. Min Act: -0.0000

Data Index: 1647099 (Python Code)

Max Activating Token Index: 450

Text #18

Max Range: 1.6022. Min Range: -1.6022

Max Act: 1.1887. Min Act: -0.0000

Data Index: 89834 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 1.6022. Min Range: -1.6022

Max Act: 0.9896. Min Act: -0.0000

Data Index: 431297 (C4 (Web Text))

Max Activating Token Index: 187