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

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

Neuron 947 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0607. Min Act: -0.0000

Data Index: 268107 (C4 (Web Text))

Max Activating Token Index: 938

Text #1

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0615. Min Act: -0.0000

Data Index: 927768 (C4 (Web Text))

Max Activating Token Index: 515

Text #2

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0606. Min Act: -0.0000

Data Index: 315099 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0636. Min Act: -0.0000

Data Index: 457505 (C4 (Web Text))

Max Activating Token Index: 909

Text #4

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0579. Min Act: -0.0000

Data Index: 1155430 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0562. Min Act: -0.0000

Data Index: 1343798 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0506. Min Act: -0.0000

Data Index: 1351222 (C4 (Web Text))

Max Activating Token Index: 230

Text #7

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0472. Min Act: -0.0000

Data Index: 314836 (C4 (Web Text))

Max Activating Token Index: 800

Text #8

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0539. Min Act: -0.0000

Data Index: 493190 (C4 (Web Text))

Max Activating Token Index: 946

Text #9

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0553. Min Act: -0.0000

Data Index: 115716 (C4 (Web Text))

Max Activating Token Index: 886

Text #10

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0514. Min Act: -0.0000

Data Index: 947964 (C4 (Web Text))

Max Activating Token Index: 472

Text #11

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0490. Min Act: -0.0000

Data Index: 1319269 (C4 (Web Text))

Max Activating Token Index: 302

Text #12

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0501. Min Act: -0.0000

Data Index: 929898 (C4 (Web Text))

Max Activating Token Index: 524

Text #13

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0497. Min Act: -0.0000

Data Index: 1126617 (C4 (Web Text))

Max Activating Token Index: 165

Text #14

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0465. Min Act: -0.0000

Data Index: 789652 (C4 (Web Text))

Max Activating Token Index: 190

Text #15

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0480. Min Act: -0.0000

Data Index: 1168309 (C4 (Web Text))

Max Activating Token Index: 823

Text #16

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0452. Min Act: -0.0000

Data Index: 1468666 (Python Code)

Max Activating Token Index: 380

Text #17

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0483. Min Act: -0.0000

Data Index: 980440 (C4 (Web Text))

Max Activating Token Index: 638

Text #18

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0492. Min Act: -0.0000

Data Index: 472908 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0483. Min Act: -0.0000

Data Index: 646802 (C4 (Web Text))

Max Activating Token Index: 21