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

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

Neuron 3612 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1697. Min Range: -3.1697

Max Act: 3.1697. Min Act: -0.0000

Data Index: 1501555 (Python Code)

Max Activating Token Index: 278

Text #1

Max Range: 3.1697. Min Range: -3.1697

Max Act: 2.6831. Min Act: -0.0000

Data Index: 1565037 (Python Code)

Max Activating Token Index: 24

Text #2

Max Range: 3.1697. Min Range: -3.1697

Max Act: 2.7858. Min Act: -0.0000

Data Index: 1637760 (Python Code)

Max Activating Token Index: 582

Text #3

Max Range: 3.1697. Min Range: -3.1697

Max Act: 2.5128. Min Act: 0.0001

Data Index: 980182 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 3.1697. Min Range: -3.1697

Max Act: 2.4763. Min Act: -0.0000

Data Index: 1503043 (Python Code)

Max Activating Token Index: 759

Text #5

Max Range: 3.1697. Min Range: -3.1697

Max Act: 2.5842. Min Act: 0.0000

Data Index: 189780 (C4 (Web Text))

Max Activating Token Index: 129

Text #6

Max Range: 3.1697. Min Range: -3.1697

Max Act: 2.5262. Min Act: -0.0000

Data Index: 1637990 (Python Code)

Max Activating Token Index: 348

Text #7

Max Range: 3.1697. Min Range: -3.1697

Max Act: 2.5836. Min Act: -0.0000

Data Index: 1654212 (Python Code)

Max Activating Token Index: 606

Text #8

Max Range: 3.1697. Min Range: -3.1697

Max Act: 2.5210. Min Act: -0.0000

Data Index: 1594912 (Python Code)

Max Activating Token Index: 523

Text #9

Max Range: 3.1697. Min Range: -3.1697

Max Act: 2.4618. Min Act: -0.0000

Data Index: 1389792 (Python Code)

Max Activating Token Index: 112

Text #10

Max Range: 3.1697. Min Range: -3.1697

Max Act: 2.4281. Min Act: -0.0000

Data Index: 15234 (C4 (Web Text))

Max Activating Token Index: 403

Text #11

Max Range: 3.1697. Min Range: -3.1697

Max Act: 2.3979. Min Act: -0.0000

Data Index: 1538881 (Python Code)

Max Activating Token Index: 64

Text #12

Max Range: 3.1697. Min Range: -3.1697

Max Act: 2.3207. Min Act: -0.0000

Data Index: 995228 (C4 (Web Text))

Max Activating Token Index: 487

Text #13

Max Range: 3.1697. Min Range: -3.1697

Max Act: 2.3151. Min Act: -0.0000

Data Index: 1128357 (C4 (Web Text))

Max Activating Token Index: 321

Text #14

Max Range: 3.1697. Min Range: -3.1697

Max Act: 2.2985. Min Act: -0.0000

Data Index: 1362581 (Python Code)

Max Activating Token Index: 542

Text #15

Max Range: 3.1697. Min Range: -3.1697

Max Act: 2.3008. Min Act: 0.0000

Data Index: 1333238 (C4 (Web Text))

Max Activating Token Index: 663

Text #16

Max Range: 3.1697. Min Range: -3.1697

Max Act: 2.2449. Min Act: -0.0000

Data Index: 274421 (C4 (Web Text))

Max Activating Token Index: 464

Text #17

Max Range: 3.1697. Min Range: -3.1697

Max Act: 2.2682. Min Act: 0.0000

Data Index: 1513909 (Python Code)

Max Activating Token Index: 120

Text #18

Max Range: 3.1697. Min Range: -3.1697

Max Act: 2.2465. Min Act: -0.0000

Data Index: 1460667 (Python Code)

Max Activating Token Index: 96

Text #19

Max Range: 3.1697. Min Range: -3.1697

Max Act: 2.2377. Min Act: -0.0000

Data Index: 1600486 (Python Code)

Max Activating Token Index: 451