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

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

Neuron 1950 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: 0.0846. Min Range: -0.0846

Max Act: 0.0846. Min Act: -0.0002

Data Index: 1032181 (C4 (Web Text))

Max Activating Token Index: 904

Text #1

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0819. Min Act: -0.0002

Data Index: 590425 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0831. Min Act: -0.0002

Data Index: 1542122 (Python Code)

Max Activating Token Index: 143

Text #3

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0807. Min Act: -0.0002

Data Index: 42501 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0796. Min Act: -0.0002

Data Index: 56306 (C4 (Web Text))

Max Activating Token Index: 874

Text #5

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0777. Min Act: -0.0002

Data Index: 1317991 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0775. Min Act: -0.0002

Data Index: 795512 (C4 (Web Text))

Max Activating Token Index: 738

Text #7

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0759. Min Act: -0.0002

Data Index: 1586791 (Python Code)

Max Activating Token Index: 156

Text #8

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0752. Min Act: -0.0002

Data Index: 852986 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0754. Min Act: -0.0002

Data Index: 23779 (C4 (Web Text))

Max Activating Token Index: 876

Text #10

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0748. Min Act: -0.0002

Data Index: 186882 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0758. Min Act: -0.0002

Data Index: 463274 (C4 (Web Text))

Max Activating Token Index: 172

Text #12

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0772. Min Act: -0.0002

Data Index: 937954 (C4 (Web Text))

Max Activating Token Index: 328

Text #13

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0762. Min Act: -0.0002

Data Index: 1335056 (C4 (Web Text))

Max Activating Token Index: 657

Text #14

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0735. Min Act: -0.0002

Data Index: 1303622 (C4 (Web Text))

Max Activating Token Index: 308

Text #15

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0731. Min Act: -0.0002

Data Index: 1097104 (C4 (Web Text))

Max Activating Token Index: 668

Text #16

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0738. Min Act: -0.0002

Data Index: 451749 (C4 (Web Text))

Max Activating Token Index: 680

Text #17

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0742. Min Act: -0.0002

Data Index: 475036 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0728. Min Act: -0.0002

Data Index: 227542 (C4 (Web Text))

Max Activating Token Index: 930

Text #19

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0726. Min Act: -0.0002

Data Index: 1286361 (C4 (Web Text))

Max Activating Token Index: 204