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

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

Neuron 5963 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9901. Min Range: -0.9901

Max Act: 0.9901. Min Act: -0.0000

Data Index: 1510702 (Python Code)

Max Activating Token Index: 70

Text #1

Max Range: 0.9901. Min Range: -0.9901

Max Act: 0.8830. Min Act: -0.0000

Data Index: 391775 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 0.9901. Min Range: -0.9901

Max Act: 0.7119. Min Act: -0.0000

Data Index: 1590433 (Python Code)

Max Activating Token Index: 281

Text #3

Max Range: 0.9901. Min Range: -0.9901

Max Act: 0.6401. Min Act: -0.0000

Data Index: 1400303 (Python Code)

Max Activating Token Index: 211

Text #4

Max Range: 0.9901. Min Range: -0.9901

Max Act: 0.6671. Min Act: -0.0000

Data Index: 568541 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 0.9901. Min Range: -0.9901

Max Act: 0.6270. Min Act: -0.0000

Data Index: 1640335 (Python Code)

Max Activating Token Index: 253

Text #6

Max Range: 0.9901. Min Range: -0.9901

Max Act: 0.6736. Min Act: -0.0000

Data Index: 1532502 (Python Code)

Max Activating Token Index: 839

Text #7

Max Range: 0.9901. Min Range: -0.9901

Max Act: 0.6056. Min Act: -0.0000

Data Index: 1526672 (Python Code)

Max Activating Token Index: 395

Text #8

Max Range: 0.9901. Min Range: -0.9901

Max Act: 0.5973. Min Act: -0.0000

Data Index: 1497895 (Python Code)

Max Activating Token Index: 24

Text #9

Max Range: 0.9901. Min Range: -0.9901

Max Act: 0.5738. Min Act: -0.0000

Data Index: 1378904 (Python Code)

Max Activating Token Index: 293

Text #10

Max Range: 0.9901. Min Range: -0.9901

Max Act: 0.5533. Min Act: -0.0000

Data Index: 1482537 (Python Code)

Max Activating Token Index: 646

Text #11

Max Range: 0.9901. Min Range: -0.9901

Max Act: 0.5709. Min Act: -0.0000

Data Index: 1558689 (Python Code)

Max Activating Token Index: 864

Text #12

Max Range: 0.9901. Min Range: -0.9901

Max Act: 0.5741. Min Act: -0.0000

Data Index: 1314542 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 0.9901. Min Range: -0.9901

Max Act: 0.5660. Min Act: -0.0000

Data Index: 1457778 (Python Code)

Max Activating Token Index: 83

Text #14

Max Range: 0.9901. Min Range: -0.9901

Max Act: 0.5607. Min Act: -0.0000

Data Index: 1355039 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 0.9901. Min Range: -0.9901

Max Act: 0.5577. Min Act: -0.0000

Data Index: 1512390 (Python Code)

Max Activating Token Index: 649

Text #16

Max Range: 0.9901. Min Range: -0.9901

Max Act: 0.5257. Min Act: -0.0000

Data Index: 1440999 (Python Code)

Max Activating Token Index: 152

Text #17

Max Range: 0.9901. Min Range: -0.9901

Max Act: 0.5364. Min Act: -0.0000

Data Index: 1409249 (Python Code)

Max Activating Token Index: 165

Text #18

Max Range: 0.9901. Min Range: -0.9901

Max Act: 0.5341. Min Act: -0.0000

Data Index: 1550891 (Python Code)

Max Activating Token Index: 291

Text #19

Max Range: 0.9901. Min Range: -0.9901

Max Act: 0.5128. Min Act: -0.0000

Data Index: 1538851 (Python Code)

Max Activating Token Index: 395