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

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

Neuron 4956 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: 0.0996. Min Range: -0.0996

Max Act: 0.0996. Min Act: -0.0002

Data Index: 1389274 (Python Code)

Max Activating Token Index: 923

Text #1

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0863. Min Act: -0.0002

Data Index: 1407753 (Python Code)

Max Activating Token Index: 943

Text #2

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0801. Min Act: -0.0002

Data Index: 890845 (C4 (Web Text))

Max Activating Token Index: 866

Text #3

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0789. Min Act: -0.0002

Data Index: 1379401 (Python Code)

Max Activating Token Index: 862

Text #4

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0767. Min Act: -0.0002

Data Index: 1208933 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0777. Min Act: -0.0002

Data Index: 387766 (C4 (Web Text))

Max Activating Token Index: 605

Text #6

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0755. Min Act: -0.0002

Data Index: 1529460 (Python Code)

Max Activating Token Index: 598

Text #7

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0758. Min Act: -0.0002

Data Index: 1623607 (Python Code)

Max Activating Token Index: 873

Text #8

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0747. Min Act: -0.0002

Data Index: 1420840 (Python Code)

Max Activating Token Index: 279

Text #9

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0762. Min Act: -0.0002

Data Index: 999804 (C4 (Web Text))

Max Activating Token Index: 3

Text #10

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0753. Min Act: -0.0002

Data Index: 1282151 (C4 (Web Text))

Max Activating Token Index: 3

Text #11

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0757. Min Act: -0.0002

Data Index: 852779 (C4 (Web Text))

Max Activating Token Index: 2

Text #12

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0729. Min Act: -0.0002

Data Index: 133682 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0730. Min Act: -0.0002

Data Index: 1437017 (Python Code)

Max Activating Token Index: 6

Text #14

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0728. Min Act: -0.0002

Data Index: 810010 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0731. Min Act: -0.0002

Data Index: 67642 (C4 (Web Text))

Max Activating Token Index: 701

Text #16

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0744. Min Act: -0.0002

Data Index: 663921 (C4 (Web Text))

Max Activating Token Index: 598

Text #17

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0736. Min Act: -0.0002

Data Index: 1445890 (Python Code)

Max Activating Token Index: 959

Text #18

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0721. Min Act: -0.0002

Data Index: 1337434 (C4 (Web Text))

Max Activating Token Index: 994

Text #19

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0709. Min Act: -0.0002

Data Index: 1535342 (Python Code)

Max Activating Token Index: 3