Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 79 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3774. Min Range: -1.3774

Max Act: 1.3774. Min Act: -0.0001

Data Index: 1590911 (Python Code)

Max Activating Token Index: 7

Text #1

Max Range: 1.3774. Min Range: -1.3774

Max Act: 1.3220. Min Act: -0.0001

Data Index: 1640839 (Python Code)

Max Activating Token Index: 5

Text #2

Max Range: 1.3774. Min Range: -1.3774

Max Act: 1.2694. Min Act: -0.0001

Data Index: 1410531 (Python Code)

Max Activating Token Index: 17

Text #3

Max Range: 1.3774. Min Range: -1.3774

Max Act: 1.2449. Min Act: -0.0001

Data Index: 1599506 (Python Code)

Max Activating Token Index: 5

Text #4

Max Range: 1.3774. Min Range: -1.3774

Max Act: 1.2533. Min Act: -0.0001

Data Index: 1390213 (Python Code)

Max Activating Token Index: 8

Text #5

Max Range: 1.3774. Min Range: -1.3774

Max Act: 1.2533. Min Act: -0.0001

Data Index: 1533764 (Python Code)

Max Activating Token Index: 8

Text #6

Max Range: 1.3774. Min Range: -1.3774

Max Act: 1.2518. Min Act: -0.0001

Data Index: 1541196 (Python Code)

Max Activating Token Index: 9

Text #7

Max Range: 1.3774. Min Range: -1.3774

Max Act: 1.2394. Min Act: -0.0001

Data Index: 1529725 (Python Code)

Max Activating Token Index: 28

Text #8

Max Range: 1.3774. Min Range: -1.3774

Max Act: 1.1923. Min Act: -0.0001

Data Index: 1619419 (Python Code)

Max Activating Token Index: 12

Text #9

Max Range: 1.3774. Min Range: -1.3774

Max Act: 1.1925. Min Act: -0.0001

Data Index: 1519258 (Python Code)

Max Activating Token Index: 21

Text #10

Max Range: 1.3774. Min Range: -1.3774

Max Act: 1.1742. Min Act: -0.0001

Data Index: 1517445 (Python Code)

Max Activating Token Index: 6

Text #11

Max Range: 1.3774. Min Range: -1.3774

Max Act: 1.2538. Min Act: -0.0001

Data Index: 1616461 (Python Code)

Max Activating Token Index: 10

Text #12

Max Range: 1.3774. Min Range: -1.3774

Max Act: 1.2538. Min Act: -0.0001

Data Index: 1518570 (Python Code)

Max Activating Token Index: 10

Text #13

Max Range: 1.3774. Min Range: -1.3774

Max Act: 1.1883. Min Act: -0.0001

Data Index: 1534920 (Python Code)

Max Activating Token Index: 7

Text #14

Max Range: 1.3774. Min Range: -1.3774

Max Act: 1.1109. Min Act: -0.0001

Data Index: 1360188 (Python Code)

Max Activating Token Index: 19

Text #15

Max Range: 1.3774. Min Range: -1.3774

Max Act: 1.1250. Min Act: -0.0001

Data Index: 1599608 (Python Code)

Max Activating Token Index: 22

Text #16

Max Range: 1.3774. Min Range: -1.3774

Max Act: 1.1631. Min Act: -0.0001

Data Index: 1426757 (Python Code)

Max Activating Token Index: 16

Text #17

Max Range: 1.3774. Min Range: -1.3774

Max Act: 1.1251. Min Act: -0.0001

Data Index: 1385689 (Python Code)

Max Activating Token Index: 8

Text #18

Max Range: 1.3774. Min Range: -1.3774

Max Act: 1.1041. Min Act: -0.0001

Data Index: 1655550 (Python Code)

Max Activating Token Index: 26

Text #19

Max Range: 1.3774. Min Range: -1.3774

Max Act: 1.0522. Min Act: -0.0001

Data Index: 1426605 (Python Code)

Max Activating Token Index: 7