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

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

Neuron 3558 in Layer 1

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: 0.0001. Min Range: -0.0001

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1040987 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0001. Min Act: -0.0002

Data Index: 426911 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0001. Min Act: -0.0003

Data Index: 1319762 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0001. Min Act: -0.0003

Data Index: 639627 (C4 (Web Text))

Max Activating Token Index: 5

Text #4

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0002

Data Index: 109114 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1081935 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0003

Data Index: 625528 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0003

Data Index: 263007 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0003

Data Index: 453487 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1035370 (C4 (Web Text))

Max Activating Token Index: 3

Text #10

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1596981 (Python Code)

Max Activating Token Index: 48

Text #11

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1437076 (Python Code)

Max Activating Token Index: 34

Text #12

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1126819 (C4 (Web Text))

Max Activating Token Index: 25

Text #13

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1495788 (Python Code)

Max Activating Token Index: 27

Text #14

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0003

Data Index: 1259287 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1438131 (Python Code)

Max Activating Token Index: 33

Text #16

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1180806 (C4 (Web Text))

Max Activating Token Index: 6

Text #17

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1420532 (Python Code)

Max Activating Token Index: 41

Text #18

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1475905 (Python Code)

Max Activating Token Index: 21

Text #19

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0002

Data Index: 436867 (C4 (Web Text))

Max Activating Token Index: 115