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

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

Neuron 21 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0697. Min Act: -0.0000

Data Index: 1656801 (Python Code)

Max Activating Token Index: 859

Text #1

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0575. Min Act: -0.0000

Data Index: 1412875 (Python Code)

Max Activating Token Index: 989

Text #2

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0536. Min Act: -0.0000

Data Index: 1597068 (Python Code)

Max Activating Token Index: 286

Text #3

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0505. Min Act: -0.0000

Data Index: 165673 (C4 (Web Text))

Max Activating Token Index: 659

Text #4

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0501. Min Act: -0.0000

Data Index: 1651276 (Python Code)

Max Activating Token Index: 964

Text #5

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0488. Min Act: -0.0000

Data Index: 1533224 (Python Code)

Max Activating Token Index: 674

Text #6

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0481. Min Act: -0.0000

Data Index: 1507675 (Python Code)

Max Activating Token Index: 458

Text #7

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0491. Min Act: -0.0000

Data Index: 1378604 (Python Code)

Max Activating Token Index: 727

Text #8

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0462. Min Act: -0.0000

Data Index: 1569471 (Python Code)

Max Activating Token Index: 939

Text #9

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0441. Min Act: -0.0000

Data Index: 330842 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0456. Min Act: -0.0000

Data Index: 1569973 (Python Code)

Max Activating Token Index: 956

Text #11

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0490. Min Act: -0.0000

Data Index: 1459067 (Python Code)

Max Activating Token Index: 871

Text #12

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0467. Min Act: -0.0000

Data Index: 1519213 (Python Code)

Max Activating Token Index: 638

Text #13

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0427. Min Act: -0.0000

Data Index: 1261956 (C4 (Web Text))

Max Activating Token Index: 693

Text #14

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0480. Min Act: -0.0000

Data Index: 1208548 (C4 (Web Text))

Max Activating Token Index: 806

Text #15

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0426. Min Act: -0.0000

Data Index: 411234 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0424. Min Act: -0.0000

Data Index: 1491554 (Python Code)

Max Activating Token Index: 522

Text #17

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0396. Min Act: -0.0000

Data Index: 1641570 (Python Code)

Max Activating Token Index: 832

Text #18

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0407. Min Act: -0.0000

Data Index: 1312532 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0408. Min Act: -0.0000

Data Index: 1259696 (C4 (Web Text))

Max Activating Token Index: 997