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

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

Neuron 3891 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: 0.3787. Min Range: -0.3787

Max Act: 0.3787. Min Act: -0.0000

Data Index: 1613465 (Python Code)

Max Activating Token Index: 86

Text #1

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.3516. Min Act: -0.0000

Data Index: 1392701 (Python Code)

Max Activating Token Index: 667

Text #2

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.3448. Min Act: -0.0000

Data Index: 1380817 (Python Code)

Max Activating Token Index: 892

Text #3

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2881. Min Act: -0.0000

Data Index: 1432400 (Python Code)

Max Activating Token Index: 156

Text #4

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.3103. Min Act: -0.0000

Data Index: 1612771 (Python Code)

Max Activating Token Index: 751

Text #5

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2822. Min Act: -0.0000

Data Index: 1424548 (Python Code)

Max Activating Token Index: 360

Text #6

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2624. Min Act: -0.0000

Data Index: 1417544 (Python Code)

Max Activating Token Index: 1000

Text #7

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2613. Min Act: -0.0000

Data Index: 1417039 (Python Code)

Max Activating Token Index: 580

Text #8

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2548. Min Act: -0.0000

Data Index: 1462697 (Python Code)

Max Activating Token Index: 722

Text #9

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2539. Min Act: -0.0000

Data Index: 1611890 (Python Code)

Max Activating Token Index: 596

Text #10

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2663. Min Act: -0.0000

Data Index: 1655719 (Python Code)

Max Activating Token Index: 911

Text #11

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2472. Min Act: -0.0000

Data Index: 1365905 (Python Code)

Max Activating Token Index: 584

Text #12

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2544. Min Act: -0.0000

Data Index: 1146167 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2432. Min Act: -0.0000

Data Index: 1533198 (Python Code)

Max Activating Token Index: 914

Text #14

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2571. Min Act: -0.0000

Data Index: 1519329 (Python Code)

Max Activating Token Index: 903

Text #15

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2651. Min Act: -0.0000

Data Index: 1434541 (Python Code)

Max Activating Token Index: 959

Text #16

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2198. Min Act: -0.0000

Data Index: 1475785 (Python Code)

Max Activating Token Index: 944

Text #17

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2340. Min Act: -0.0000

Data Index: 1479525 (Python Code)

Max Activating Token Index: 998

Text #18

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2572. Min Act: -0.0000

Data Index: 1625284 (Python Code)

Max Activating Token Index: 839

Text #19

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2166. Min Act: -0.0000

Data Index: 1412866 (Python Code)

Max Activating Token Index: 136