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

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

Neuron 2664 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5376. Min Range: -1.5376

Max Act: 1.5376. Min Act: -0.0000

Data Index: 1529035 (Python Code)

Max Activating Token Index: 612

Text #1

Max Range: 1.5376. Min Range: -1.5376

Max Act: 1.4893. Min Act: -0.0000

Data Index: 1530468 (Python Code)

Max Activating Token Index: 662

Text #2

Max Range: 1.5376. Min Range: -1.5376

Max Act: 1.4167. Min Act: -0.0000

Data Index: 1622806 (Python Code)

Max Activating Token Index: 131

Text #3

Max Range: 1.5376. Min Range: -1.5376

Max Act: 1.2390. Min Act: -0.0000

Data Index: 1386252 (Python Code)

Max Activating Token Index: 732

Text #4

Max Range: 1.5376. Min Range: -1.5376

Max Act: 1.3222. Min Act: -0.0000

Data Index: 1620140 (Python Code)

Max Activating Token Index: 1008

Text #5

Max Range: 1.5376. Min Range: -1.5376

Max Act: 1.3004. Min Act: -0.0000

Data Index: 1447902 (Python Code)

Max Activating Token Index: 471

Text #6

Max Range: 1.5376. Min Range: -1.5376

Max Act: 1.2585. Min Act: -0.0000

Data Index: 1490760 (Python Code)

Max Activating Token Index: 908

Text #7

Max Range: 1.5376. Min Range: -1.5376

Max Act: 1.2718. Min Act: -0.0000

Data Index: 1536255 (Python Code)

Max Activating Token Index: 309

Text #8

Max Range: 1.5376. Min Range: -1.5376

Max Act: 1.1998. Min Act: -0.0000

Data Index: 1446723 (Python Code)

Max Activating Token Index: 241

Text #9

Max Range: 1.5376. Min Range: -1.5376

Max Act: 1.1799. Min Act: -0.0000

Data Index: 604037 (C4 (Web Text))

Max Activating Token Index: 748

Text #10

Max Range: 1.5376. Min Range: -1.5376

Max Act: 1.0831. Min Act: -0.0000

Data Index: 1631131 (Python Code)

Max Activating Token Index: 729

Text #11

Max Range: 1.5376. Min Range: -1.5376

Max Act: 1.0760. Min Act: -0.0000

Data Index: 1498125 (Python Code)

Max Activating Token Index: 870

Text #12

Max Range: 1.5376. Min Range: -1.5376

Max Act: 1.0513. Min Act: -0.0000

Data Index: 1537900 (Python Code)

Max Activating Token Index: 375

Text #13

Max Range: 1.5376. Min Range: -1.5376

Max Act: 1.0604. Min Act: -0.0000

Data Index: 1591480 (Python Code)

Max Activating Token Index: 298

Text #14

Max Range: 1.5376. Min Range: -1.5376

Max Act: 1.0554. Min Act: -0.0000

Data Index: 1407912 (Python Code)

Max Activating Token Index: 16

Text #15

Max Range: 1.5376. Min Range: -1.5376

Max Act: 1.0385. Min Act: -0.0000

Data Index: 1426819 (Python Code)

Max Activating Token Index: 679

Text #16

Max Range: 1.5376. Min Range: -1.5376

Max Act: 1.0699. Min Act: -0.0000

Data Index: 1621305 (Python Code)

Max Activating Token Index: 949

Text #17

Max Range: 1.5376. Min Range: -1.5376

Max Act: 1.0181. Min Act: -0.0000

Data Index: 1504608 (Python Code)

Max Activating Token Index: 570

Text #18

Max Range: 1.5376. Min Range: -1.5376

Max Act: 0.9922. Min Act: -0.0000

Data Index: 576790 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 1.5376. Min Range: -1.5376

Max Act: 0.8665. Min Act: -0.0000

Data Index: 1521759 (Python Code)

Max Activating Token Index: 325