Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1189 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0636. Min Act: -0.0003

Data Index: 1407698 (Python Code)

Max Activating Token Index: 14

Text #1

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0584. Min Act: -0.0003

Data Index: 1548823 (Python Code)

Max Activating Token Index: 26

Text #2

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0581. Min Act: -0.0003

Data Index: 1360094 (Python Code)

Max Activating Token Index: 5

Text #3

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0574. Min Act: -0.0003

Data Index: 1372305 (Python Code)

Max Activating Token Index: 9

Text #4

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0546. Min Act: -0.0003

Data Index: 1377053 (Python Code)

Max Activating Token Index: 16

Text #5

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0550. Min Act: -0.0003

Data Index: 1595903 (Python Code)

Max Activating Token Index: 44

Text #6

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0539. Min Act: -0.0003

Data Index: 1424947 (Python Code)

Max Activating Token Index: 8

Text #7

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0528. Min Act: -0.0003

Data Index: 1385998 (Python Code)

Max Activating Token Index: 12

Text #8

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0524. Min Act: -0.0003

Data Index: 1500085 (Python Code)

Max Activating Token Index: 10

Text #9

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0540. Min Act: -0.0003

Data Index: 1516824 (Python Code)

Max Activating Token Index: 26

Text #10

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0511. Min Act: -0.0003

Data Index: 1421403 (Python Code)

Max Activating Token Index: 30

Text #11

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0521. Min Act: -0.0003

Data Index: 1543056 (Python Code)

Max Activating Token Index: 150

Text #12

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0497. Min Act: -0.0003

Data Index: 1429999 (Python Code)

Max Activating Token Index: 26

Text #13

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0513. Min Act: -0.0003

Data Index: 1373730 (Python Code)

Max Activating Token Index: 850

Text #14

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0496. Min Act: -0.0003

Data Index: 1423180 (Python Code)

Max Activating Token Index: 24

Text #15

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0484. Min Act: -0.0002

Data Index: 1435874 (Python Code)

Max Activating Token Index: 4

Text #16

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0495. Min Act: -0.0003

Data Index: 1489475 (Python Code)

Max Activating Token Index: 11

Text #17

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0481. Min Act: -0.0003

Data Index: 1532319 (Python Code)

Max Activating Token Index: 20

Text #18

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0457. Min Act: -0.0003

Data Index: 589146 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0420. Min Act: -0.0003

Data Index: 1315852 (C4 (Web Text))

Max Activating Token Index: 619