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

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

Neuron 3984 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1555. Min Range: -4.1555

Max Act: 3.9809. Min Act: -0.0000

Data Index: 1534658 (Python Code)

Max Activating Token Index: 221

Text #1

Max Range: 4.1555. Min Range: -4.1555

Max Act: 4.1555. Min Act: -0.0000

Data Index: 1541622 (Python Code)

Max Activating Token Index: 303

Text #2

Max Range: 4.1555. Min Range: -4.1555

Max Act: 3.9828. Min Act: -0.0000

Data Index: 1628499 (Python Code)

Max Activating Token Index: 68

Text #3

Max Range: 4.1555. Min Range: -4.1555

Max Act: 3.7724. Min Act: -0.0000

Data Index: 1517812 (Python Code)

Max Activating Token Index: 182

Text #4

Max Range: 4.1555. Min Range: -4.1555

Max Act: 3.9050. Min Act: -0.0000

Data Index: 1647759 (Python Code)

Max Activating Token Index: 156

Text #5

Max Range: 4.1555. Min Range: -4.1555

Max Act: 3.9357. Min Act: -0.0000

Data Index: 1410527 (Python Code)

Max Activating Token Index: 50

Text #6

Max Range: 4.1555. Min Range: -4.1555

Max Act: 3.6065. Min Act: -0.0000

Data Index: 1647887 (Python Code)

Max Activating Token Index: 153

Text #7

Max Range: 4.1555. Min Range: -4.1555

Max Act: 3.7555. Min Act: -0.0000

Data Index: 1406222 (Python Code)

Max Activating Token Index: 268

Text #8

Max Range: 4.1555. Min Range: -4.1555

Max Act: 3.5861. Min Act: -0.0000

Data Index: 1605696 (Python Code)

Max Activating Token Index: 164

Text #9

Max Range: 4.1555. Min Range: -4.1555

Max Act: 3.6876. Min Act: -0.0000

Data Index: 1511287 (Python Code)

Max Activating Token Index: 40

Text #10

Max Range: 4.1555. Min Range: -4.1555

Max Act: 3.3744. Min Act: -0.0000

Data Index: 1547640 (Python Code)

Max Activating Token Index: 124

Text #11

Max Range: 4.1555. Min Range: -4.1555

Max Act: 3.5040. Min Act: -0.0000

Data Index: 1574023 (Python Code)

Max Activating Token Index: 322

Text #12

Max Range: 4.1555. Min Range: -4.1555

Max Act: 3.2061. Min Act: -0.0000

Data Index: 1629127 (Python Code)

Max Activating Token Index: 143

Text #13

Max Range: 4.1555. Min Range: -4.1555

Max Act: 3.6413. Min Act: -0.0000

Data Index: 1649580 (Python Code)

Max Activating Token Index: 180

Text #14

Max Range: 4.1555. Min Range: -4.1555

Max Act: 3.4759. Min Act: -0.0000

Data Index: 1648997 (Python Code)

Max Activating Token Index: 179

Text #15

Max Range: 4.1555. Min Range: -4.1555

Max Act: 3.3020. Min Act: -0.0000

Data Index: 1466008 (Python Code)

Max Activating Token Index: 41

Text #16

Max Range: 4.1555. Min Range: -4.1555

Max Act: 3.2883. Min Act: -0.0000

Data Index: 1406750 (Python Code)

Max Activating Token Index: 190

Text #17

Max Range: 4.1555. Min Range: -4.1555

Max Act: 3.2744. Min Act: -0.0000

Data Index: 1536604 (Python Code)

Max Activating Token Index: 31

Text #18

Max Range: 4.1555. Min Range: -4.1555

Max Act: 3.2884. Min Act: -0.0000

Data Index: 1525333 (Python Code)

Max Activating Token Index: 53

Text #19

Max Range: 4.1555. Min Range: -4.1555

Max Act: 3.3979. Min Act: -0.0000

Data Index: 1458520 (Python Code)

Max Activating Token Index: 11