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

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

Neuron 3890 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.9658. Min Act: -0.0001

Data Index: 1453711 (Python Code)

Max Activating Token Index: 22

Text #1

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.9727. Min Act: -0.0001

Data Index: 1399345 (Python Code)

Max Activating Token Index: 68

Text #2

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.9507. Min Act: -0.0001

Data Index: 1629145 (Python Code)

Max Activating Token Index: 22

Text #3

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.9471. Min Act: -0.0001

Data Index: 1529887 (Python Code)

Max Activating Token Index: 87

Text #4

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.9227. Min Act: -0.0001

Data Index: 1411379 (Python Code)

Max Activating Token Index: 44

Text #5

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.8958. Min Act: -0.0001

Data Index: 1503094 (Python Code)

Max Activating Token Index: 61

Text #6

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.8884. Min Act: -0.0001

Data Index: 1496549 (Python Code)

Max Activating Token Index: 77

Text #7

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.8923. Min Act: -0.0001

Data Index: 1544649 (Python Code)

Max Activating Token Index: 44

Text #8

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.8654. Min Act: -0.0001

Data Index: 1422298 (Python Code)

Max Activating Token Index: 22

Text #9

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.8828. Min Act: -0.0001

Data Index: 1412266 (Python Code)

Max Activating Token Index: 39

Text #10

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.8714. Min Act: -0.0001

Data Index: 1501919 (Python Code)

Max Activating Token Index: 103

Text #11

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.8552. Min Act: -0.0001

Data Index: 1616168 (Python Code)

Max Activating Token Index: 77

Text #12

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.8682. Min Act: -0.0001

Data Index: 1419765 (Python Code)

Max Activating Token Index: 78

Text #13

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.8823. Min Act: -0.0001

Data Index: 1572867 (Python Code)

Max Activating Token Index: 60

Text #14

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.8685. Min Act: -0.0001

Data Index: 1588224 (Python Code)

Max Activating Token Index: 21

Text #15

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.8573. Min Act: -0.0001

Data Index: 1605733 (Python Code)

Max Activating Token Index: 19

Text #16

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.8555. Min Act: -0.0001

Data Index: 1489971 (Python Code)

Max Activating Token Index: 52

Text #17

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.8654. Min Act: -0.0001

Data Index: 1376786 (Python Code)

Max Activating Token Index: 53

Text #18

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.8608. Min Act: -0.0001

Data Index: 1361153 (Python Code)

Max Activating Token Index: 53

Text #19

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.8577. Min Act: -0.0001

Data Index: 1399142 (Python Code)

Max Activating Token Index: 33