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

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

Neuron 3981 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9730. Min Range: -2.9730

Max Act: 2.9730. Min Act: -0.0000

Data Index: 1407989 (Python Code)

Max Activating Token Index: 543

Text #1

Max Range: 2.9730. Min Range: -2.9730

Max Act: 2.6776. Min Act: -0.0000

Data Index: 583353 (C4 (Web Text))

Max Activating Token Index: 134

Text #2

Max Range: 2.9730. Min Range: -2.9730

Max Act: 2.4460. Min Act: -0.0000

Data Index: 1341924 (C4 (Web Text))

Max Activating Token Index: 955

Text #3

Max Range: 2.9730. Min Range: -2.9730

Max Act: 2.1932. Min Act: -0.0000

Data Index: 1624224 (Python Code)

Max Activating Token Index: 624

Text #4

Max Range: 2.9730. Min Range: -2.9730

Max Act: 2.0458. Min Act: -0.0000

Data Index: 1369582 (Python Code)

Max Activating Token Index: 959

Text #5

Max Range: 2.9730. Min Range: -2.9730

Max Act: 1.9184. Min Act: -0.0000

Data Index: 1511545 (Python Code)

Max Activating Token Index: 98

Text #6

Max Range: 2.9730. Min Range: -2.9730

Max Act: 2.0205. Min Act: -0.0000

Data Index: 1466883 (Python Code)

Max Activating Token Index: 713

Text #7

Max Range: 2.9730. Min Range: -2.9730

Max Act: 1.9993. Min Act: -0.0000

Data Index: 1261621 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 2.9730. Min Range: -2.9730

Max Act: 2.0801. Min Act: -0.0000

Data Index: 1410484 (Python Code)

Max Activating Token Index: 734

Text #9

Max Range: 2.9730. Min Range: -2.9730

Max Act: 1.8058. Min Act: -0.0000

Data Index: 1627435 (Python Code)

Max Activating Token Index: 407

Text #10

Max Range: 2.9730. Min Range: -2.9730

Max Act: 1.8964. Min Act: -0.0000

Data Index: 1647708 (Python Code)

Max Activating Token Index: 67

Text #11

Max Range: 2.9730. Min Range: -2.9730

Max Act: 1.8690. Min Act: -0.0000

Data Index: 1483262 (Python Code)

Max Activating Token Index: 538

Text #12

Max Range: 2.9730. Min Range: -2.9730

Max Act: 1.9551. Min Act: -0.0000

Data Index: 1601223 (Python Code)

Max Activating Token Index: 737

Text #13

Max Range: 2.9730. Min Range: -2.9730

Max Act: 1.8900. Min Act: -0.0000

Data Index: 1392266 (Python Code)

Max Activating Token Index: 238

Text #14

Max Range: 2.9730. Min Range: -2.9730

Max Act: 1.8047. Min Act: -0.0000

Data Index: 1596968 (Python Code)

Max Activating Token Index: 732

Text #15

Max Range: 2.9730. Min Range: -2.9730

Max Act: 1.8081. Min Act: -0.0000

Data Index: 1446890 (Python Code)

Max Activating Token Index: 762

Text #16

Max Range: 2.9730. Min Range: -2.9730

Max Act: 1.7132. Min Act: -0.0000

Data Index: 1423509 (Python Code)

Max Activating Token Index: 744

Text #17

Max Range: 2.9730. Min Range: -2.9730

Max Act: 1.7510. Min Act: -0.0000

Data Index: 1615856 (Python Code)

Max Activating Token Index: 743

Text #18

Max Range: 2.9730. Min Range: -2.9730

Max Act: 1.7485. Min Act: -0.0000

Data Index: 1627110 (Python Code)

Max Activating Token Index: 482

Text #19

Max Range: 2.9730. Min Range: -2.9730

Max Act: 1.8689. Min Act: 0.0000

Data Index: 1425292 (Python Code)

Max Activating Token Index: 370