Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2227 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.1240. Min Act: -0.0001

Data Index: 1479169 (Python Code)

Max Activating Token Index: 11

Text #1

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.1240. Min Act: -0.0001

Data Index: 1423881 (Python Code)

Max Activating Token Index: 9

Text #2

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.1184. Min Act: -0.0001

Data Index: 1398989 (Python Code)

Max Activating Token Index: 10

Text #3

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.1103. Min Act: -0.0001

Data Index: 1394338 (Python Code)

Max Activating Token Index: 5

Text #4

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0965. Min Act: -0.0001

Data Index: 1617753 (Python Code)

Max Activating Token Index: 4

Text #5

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0833. Min Act: -0.0001

Data Index: 1572598 (Python Code)

Max Activating Token Index: 18

Text #6

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0762. Min Act: -0.0001

Data Index: 1398527 (Python Code)

Max Activating Token Index: 17

Text #7

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0772. Min Act: -0.0001

Data Index: 1587794 (Python Code)

Max Activating Token Index: 15

Text #8

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0741. Min Act: -0.0001

Data Index: 1549524 (Python Code)

Max Activating Token Index: 3

Text #9

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0756. Min Act: -0.0001

Data Index: 1619359 (Python Code)

Max Activating Token Index: 8

Text #10

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0756. Min Act: -0.0001

Data Index: 1472306 (Python Code)

Max Activating Token Index: 8

Text #11

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0679. Min Act: -0.0001

Data Index: 1432520 (Python Code)

Max Activating Token Index: 14

Text #12

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0705. Min Act: -0.0001

Data Index: 1520143 (Python Code)

Max Activating Token Index: 4

Text #13

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0705. Min Act: -0.0001

Data Index: 1373923 (Python Code)

Max Activating Token Index: 4

Text #14

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0681. Min Act: -0.0001

Data Index: 1435943 (Python Code)

Max Activating Token Index: 5

Text #15

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0697. Min Act: -0.0001

Data Index: 1640866 (Python Code)

Max Activating Token Index: 30

Text #16

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0699. Min Act: -0.0001

Data Index: 1432627 (Python Code)

Max Activating Token Index: 4

Text #17

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0699. Min Act: -0.0001

Data Index: 1598003 (Python Code)

Max Activating Token Index: 4

Text #18

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0691. Min Act: -0.0001

Data Index: 1361266 (Python Code)

Max Activating Token Index: 4

Text #19

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0712. Min Act: -0.0001

Data Index: 1627028 (Python Code)

Max Activating Token Index: 15