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

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

Neuron 3786 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0786. Min Act: -0.0001

Data Index: 1132540 (C4 (Web Text))

Max Activating Token Index: 653

Text #1

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0641. Min Act: -0.0001

Data Index: 397281 (C4 (Web Text))

Max Activating Token Index: 708

Text #2

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0643. Min Act: -0.0001

Data Index: 1469644 (Python Code)

Max Activating Token Index: 7

Text #3

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0643. Min Act: -0.0001

Data Index: 1371422 (Python Code)

Max Activating Token Index: 7

Text #4

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0625. Min Act: -0.0001

Data Index: 1438966 (Python Code)

Max Activating Token Index: 9

Text #5

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0590. Min Act: -0.0001

Data Index: 1089983 (C4 (Web Text))

Max Activating Token Index: 689

Text #6

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0560. Min Act: -0.0001

Data Index: 1483331 (Python Code)

Max Activating Token Index: 10

Text #7

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0560. Min Act: -0.0001

Data Index: 1418491 (Python Code)

Max Activating Token Index: 10

Text #8

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0560. Min Act: -0.0001

Data Index: 1482236 (Python Code)

Max Activating Token Index: 10

Text #9

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0560. Min Act: -0.0001

Data Index: 1455206 (Python Code)

Max Activating Token Index: 10

Text #10

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0562. Min Act: -0.0001

Data Index: 1598493 (Python Code)

Max Activating Token Index: 6

Text #11

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0562. Min Act: -0.0001

Data Index: 1616261 (Python Code)

Max Activating Token Index: 6

Text #12

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0553. Min Act: -0.0001

Data Index: 646933 (C4 (Web Text))

Max Activating Token Index: 912

Text #13

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0598. Min Act: -0.0001

Data Index: 1192812 (C4 (Web Text))

Max Activating Token Index: 341

Text #14

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0533. Min Act: -0.0002

Data Index: 900230 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0534. Min Act: -0.0001

Data Index: 793690 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0588. Min Act: -0.0001

Data Index: 276642 (C4 (Web Text))

Max Activating Token Index: 297

Text #17

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0518. Min Act: -0.0002

Data Index: 226403 (C4 (Web Text))

Max Activating Token Index: 883

Text #18

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0521. Min Act: -0.0001

Data Index: 1533170 (Python Code)

Max Activating Token Index: 11

Text #19

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0522. Min Act: -0.0001

Data Index: 566532 (C4 (Web Text))

Max Activating Token Index: 535