Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1073 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.2807. Min Range: -4.2807

Max Act: 4.2807. Min Act: -0.0000

Data Index: 1531890 (Python Code)

Max Activating Token Index: 88

Text #1

Max Range: 4.2807. Min Range: -4.2807

Max Act: 4.0672. Min Act: -0.0000

Data Index: 1419553 (Python Code)

Max Activating Token Index: 408

Text #2

Max Range: 4.2807. Min Range: -4.2807

Max Act: 3.6920. Min Act: -0.0000

Data Index: 1559349 (Python Code)

Max Activating Token Index: 794

Text #3

Max Range: 4.2807. Min Range: -4.2807

Max Act: 3.4632. Min Act: -0.0000

Data Index: 378425 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 4.2807. Min Range: -4.2807

Max Act: 3.2498. Min Act: -0.0000

Data Index: 1460300 (Python Code)

Max Activating Token Index: 56

Text #5

Max Range: 4.2807. Min Range: -4.2807

Max Act: 3.6174. Min Act: -0.0000

Data Index: 818623 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 4.2807. Min Range: -4.2807

Max Act: 3.3359. Min Act: -0.0000

Data Index: 1623248 (Python Code)

Max Activating Token Index: 295

Text #7

Max Range: 4.2807. Min Range: -4.2807

Max Act: 3.1780. Min Act: -0.0000

Data Index: 1393979 (Python Code)

Max Activating Token Index: 260

Text #8

Max Range: 4.2807. Min Range: -4.2807

Max Act: 3.4630. Min Act: -0.0000

Data Index: 1644577 (Python Code)

Max Activating Token Index: 881

Text #9

Max Range: 4.2807. Min Range: -4.2807

Max Act: 3.2511. Min Act: -0.0000

Data Index: 1372431 (Python Code)

Max Activating Token Index: 46

Text #10

Max Range: 4.2807. Min Range: -4.2807

Max Act: 3.3997. Min Act: -0.0000

Data Index: 1623079 (Python Code)

Max Activating Token Index: 27

Text #11

Max Range: 4.2807. Min Range: -4.2807

Max Act: 2.9787. Min Act: -0.0000

Data Index: 833448 (C4 (Web Text))

Max Activating Token Index: 175

Text #12

Max Range: 4.2807. Min Range: -4.2807

Max Act: 3.0965. Min Act: -0.0000

Data Index: 1391544 (Python Code)

Max Activating Token Index: 739

Text #13

Max Range: 4.2807. Min Range: -4.2807

Max Act: 2.9287. Min Act: -0.0000

Data Index: 502684 (C4 (Web Text))

Max Activating Token Index: 813

Text #14

Max Range: 4.2807. Min Range: -4.2807

Max Act: 3.0829. Min Act: -0.0000

Data Index: 1637054 (Python Code)

Max Activating Token Index: 657

Text #15

Max Range: 4.2807. Min Range: -4.2807

Max Act: 3.0404. Min Act: -0.0000

Data Index: 1328831 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 4.2807. Min Range: -4.2807

Max Act: 3.7243. Min Act: -0.0000

Data Index: 1533540 (Python Code)

Max Activating Token Index: 182

Text #17

Max Range: 4.2807. Min Range: -4.2807

Max Act: 2.8682. Min Act: -0.0000

Data Index: 1076631 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 4.2807. Min Range: -4.2807

Max Act: 3.0120. Min Act: -0.0000

Data Index: 1494246 (Python Code)

Max Activating Token Index: 524

Text #19

Max Range: 4.2807. Min Range: -4.2807

Max Act: 2.9866. Min Act: -0.0000

Data Index: 1395268 (Python Code)

Max Activating Token Index: 969