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

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

Neuron 1360 in Layer 0

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: 0.0396. Min Range: -0.0396

Max Act: 0.0396. Min Act: -0.0001

Data Index: 895278 (C4 (Web Text))

Max Activating Token Index: 1

Text #1

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0396. Min Act: -0.0001

Data Index: 1137592 (C4 (Web Text))

Max Activating Token Index: 1

Text #2

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0396. Min Act: -0.0001

Data Index: 464034 (C4 (Web Text))

Max Activating Token Index: 1

Text #3

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0396. Min Act: -0.0001

Data Index: 840577 (C4 (Web Text))

Max Activating Token Index: 1

Text #4

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0327. Min Act: -0.0001

Data Index: 1434633 (Python Code)

Max Activating Token Index: 1

Text #5

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0327. Min Act: -0.0001

Data Index: 1366581 (Python Code)

Max Activating Token Index: 1

Text #6

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0327. Min Act: -0.0001

Data Index: 60871 (C4 (Web Text))

Max Activating Token Index: 1

Text #7

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0327. Min Act: -0.0001

Data Index: 66453 (C4 (Web Text))

Max Activating Token Index: 1

Text #8

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0327. Min Act: -0.0002

Data Index: 66571 (C4 (Web Text))

Max Activating Token Index: 1

Text #9

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0327. Min Act: -0.0001

Data Index: 69223 (C4 (Web Text))

Max Activating Token Index: 1

Text #10

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0327. Min Act: -0.0001

Data Index: 71267 (C4 (Web Text))

Max Activating Token Index: 1

Text #11

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0327. Min Act: -0.0001

Data Index: 73776 (C4 (Web Text))

Max Activating Token Index: 1

Text #12

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0327. Min Act: -0.0001

Data Index: 76485 (C4 (Web Text))

Max Activating Token Index: 1

Text #13

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0327. Min Act: -0.0001

Data Index: 79566 (C4 (Web Text))

Max Activating Token Index: 1

Text #14

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0327. Min Act: -0.0001

Data Index: 77146 (C4 (Web Text))

Max Activating Token Index: 1

Text #15

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0327. Min Act: -0.0001

Data Index: 98019 (C4 (Web Text))

Max Activating Token Index: 1

Text #16

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0327. Min Act: -0.0001

Data Index: 97929 (C4 (Web Text))

Max Activating Token Index: 1

Text #17

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0327. Min Act: -0.0001

Data Index: 97511 (C4 (Web Text))

Max Activating Token Index: 1

Text #18

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0327. Min Act: -0.0001

Data Index: 96277 (C4 (Web Text))

Max Activating Token Index: 1

Text #19

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0327. Min Act: -0.0001

Data Index: 94688 (C4 (Web Text))

Max Activating Token Index: 1