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

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

Neuron 695 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9875. Min Range: -0.9875

Max Act: 0.9815. Min Act: -0.0000

Data Index: 1430902 (Python Code)

Max Activating Token Index: 166

Text #1

Max Range: 0.9875. Min Range: -0.9875

Max Act: 0.9875. Min Act: -0.0000

Data Index: 1406395 (Python Code)

Max Activating Token Index: 44

Text #2

Max Range: 0.9875. Min Range: -0.9875

Max Act: 0.9716. Min Act: -0.0000

Data Index: 1410608 (Python Code)

Max Activating Token Index: 211

Text #3

Max Range: 0.9875. Min Range: -0.9875

Max Act: 0.9781. Min Act: -0.0000

Data Index: 542120 (C4 (Web Text))

Max Activating Token Index: 829

Text #4

Max Range: 0.9875. Min Range: -0.9875

Max Act: 0.8577. Min Act: -0.0000

Data Index: 1412580 (Python Code)

Max Activating Token Index: 39

Text #5

Max Range: 0.9875. Min Range: -0.9875

Max Act: 0.9298. Min Act: -0.0000

Data Index: 672547 (C4 (Web Text))

Max Activating Token Index: 313

Text #6

Max Range: 0.9875. Min Range: -0.9875

Max Act: 0.9319. Min Act: -0.0000

Data Index: 1495772 (Python Code)

Max Activating Token Index: 294

Text #7

Max Range: 0.9875. Min Range: -0.9875

Max Act: 0.8595. Min Act: -0.0000

Data Index: 561482 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 0.9875. Min Range: -0.9875

Max Act: 0.7800. Min Act: -0.0000

Data Index: 1416306 (Python Code)

Max Activating Token Index: 484

Text #9

Max Range: 0.9875. Min Range: -0.9875

Max Act: 0.7479. Min Act: -0.0000

Data Index: 1459036 (Python Code)

Max Activating Token Index: 882

Text #10

Max Range: 0.9875. Min Range: -0.9875

Max Act: 0.8325. Min Act: -0.0000

Data Index: 113820 (C4 (Web Text))

Max Activating Token Index: 358

Text #11

Max Range: 0.9875. Min Range: -0.9875

Max Act: 0.7682. Min Act: -0.0000

Data Index: 798606 (C4 (Web Text))

Max Activating Token Index: 232

Text #12

Max Range: 0.9875. Min Range: -0.9875

Max Act: 0.7143. Min Act: -0.0000

Data Index: 490281 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 0.9875. Min Range: -0.9875

Max Act: 0.7198. Min Act: -0.0000

Data Index: 1656860 (Python Code)

Max Activating Token Index: 444

Text #14

Max Range: 0.9875. Min Range: -0.9875

Max Act: 0.8204. Min Act: -0.0000

Data Index: 1453957 (Python Code)

Max Activating Token Index: 923

Text #15

Max Range: 0.9875. Min Range: -0.9875

Max Act: 0.7158. Min Act: -0.0000

Data Index: 654488 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 0.9875. Min Range: -0.9875

Max Act: 0.6588. Min Act: -0.0000

Data Index: 238219 (C4 (Web Text))

Max Activating Token Index: 633

Text #17

Max Range: 0.9875. Min Range: -0.9875

Max Act: 0.7286. Min Act: -0.0000

Data Index: 84602 (C4 (Web Text))

Max Activating Token Index: 308

Text #18

Max Range: 0.9875. Min Range: -0.9875

Max Act: 0.7059. Min Act: -0.0000

Data Index: 379408 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 0.9875. Min Range: -0.9875

Max Act: 0.6250. Min Act: -0.0000

Data Index: 400884 (C4 (Web Text))

Max Activating Token Index: 396