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

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

Neuron 3953 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: 3.2582. Min Range: -3.2582

Max Act: 3.2582. Min Act: -0.0000

Data Index: 1124775 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 3.2582. Min Range: -3.2582

Max Act: 3.0971. Min Act: -0.0000

Data Index: 1565703 (Python Code)

Max Activating Token Index: 961

Text #2

Max Range: 3.2582. Min Range: -3.2582

Max Act: 2.5331. Min Act: -0.0000

Data Index: 399029 (C4 (Web Text))

Max Activating Token Index: 450

Text #3

Max Range: 3.2582. Min Range: -3.2582

Max Act: 2.7426. Min Act: -0.0000

Data Index: 1599495 (Python Code)

Max Activating Token Index: 543

Text #4

Max Range: 3.2582. Min Range: -3.2582

Max Act: 2.8021. Min Act: -0.0000

Data Index: 1492247 (Python Code)

Max Activating Token Index: 548

Text #5

Max Range: 3.2582. Min Range: -3.2582

Max Act: 2.8227. Min Act: -0.0000

Data Index: 1389914 (Python Code)

Max Activating Token Index: 390

Text #6

Max Range: 3.2582. Min Range: -3.2582

Max Act: 2.8089. Min Act: -0.0000

Data Index: 1474113 (Python Code)

Max Activating Token Index: 608

Text #7

Max Range: 3.2582. Min Range: -3.2582

Max Act: 2.4639. Min Act: -0.0000

Data Index: 843761 (C4 (Web Text))

Max Activating Token Index: 848

Text #8

Max Range: 3.2582. Min Range: -3.2582

Max Act: 2.6154. Min Act: -0.0000

Data Index: 284188 (C4 (Web Text))

Max Activating Token Index: 325

Text #9

Max Range: 3.2582. Min Range: -3.2582

Max Act: 2.7160. Min Act: -0.0000

Data Index: 344406 (C4 (Web Text))

Max Activating Token Index: 555

Text #10

Max Range: 3.2582. Min Range: -3.2582

Max Act: 2.5132. Min Act: 0.0000

Data Index: 1187989 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 3.2582. Min Range: -3.2582

Max Act: 2.3346. Min Act: -0.0000

Data Index: 1643126 (Python Code)

Max Activating Token Index: 292

Text #12

Max Range: 3.2582. Min Range: -3.2582

Max Act: 2.5275. Min Act: -0.0000

Data Index: 1479829 (Python Code)

Max Activating Token Index: 1004

Text #13

Max Range: 3.2582. Min Range: -3.2582

Max Act: 2.4341. Min Act: -0.0000

Data Index: 851366 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 3.2582. Min Range: -3.2582

Max Act: 2.2814. Min Act: -0.0000

Data Index: 1639132 (Python Code)

Max Activating Token Index: 519

Text #15

Max Range: 3.2582. Min Range: -3.2582

Max Act: 1.9683. Min Act: -0.0000

Data Index: 1455917 (Python Code)

Max Activating Token Index: 818

Text #16

Max Range: 3.2582. Min Range: -3.2582

Max Act: 2.3284. Min Act: -0.0000

Data Index: 1530055 (Python Code)

Max Activating Token Index: 219

Text #17

Max Range: 3.2582. Min Range: -3.2582

Max Act: 2.3413. Min Act: -0.0000

Data Index: 1568843 (Python Code)

Max Activating Token Index: 960

Text #18

Max Range: 3.2582. Min Range: -3.2582

Max Act: 2.1827. Min Act: -0.0000

Data Index: 1541212 (Python Code)

Max Activating Token Index: 582

Text #19

Max Range: 3.2582. Min Range: -3.2582

Max Act: 2.2230. Min Act: -0.0000

Data Index: 1411278 (Python Code)

Max Activating Token Index: 166