Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1473 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.3207. Min Act: -0.0002

Data Index: 1361318 (Python Code)

Max Activating Token Index: 808

Text #1

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.3120. Min Act: -0.0002

Data Index: 1517138 (Python Code)

Max Activating Token Index: 399

Text #2

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2955. Min Act: -0.0002

Data Index: 1381697 (Python Code)

Max Activating Token Index: 892

Text #3

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2812. Min Act: -0.0002

Data Index: 1528614 (Python Code)

Max Activating Token Index: 824

Text #4

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2897. Min Act: -0.0002

Data Index: 1451210 (Python Code)

Max Activating Token Index: 606

Text #5

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2966. Min Act: -0.0002

Data Index: 1461963 (Python Code)

Max Activating Token Index: 878

Text #6

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.3066. Min Act: -0.0002

Data Index: 1413951 (Python Code)

Max Activating Token Index: 259

Text #7

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2824. Min Act: -0.0002

Data Index: 1485128 (Python Code)

Max Activating Token Index: 272

Text #8

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2801. Min Act: -0.0002

Data Index: 1451623 (Python Code)

Max Activating Token Index: 848

Text #9

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2725. Min Act: -0.0002

Data Index: 1609678 (Python Code)

Max Activating Token Index: 114

Text #10

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2638. Min Act: -0.0002

Data Index: 1378459 (Python Code)

Max Activating Token Index: 723

Text #11

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2799. Min Act: -0.0002

Data Index: 1507709 (Python Code)

Max Activating Token Index: 815

Text #12

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2756. Min Act: -0.0002

Data Index: 1522915 (Python Code)

Max Activating Token Index: 305

Text #13

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2716. Min Act: -0.0002

Data Index: 1547432 (Python Code)

Max Activating Token Index: 283

Text #14

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2693. Min Act: -0.0002

Data Index: 1570306 (Python Code)

Max Activating Token Index: 888

Text #15

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2684. Min Act: -0.0002

Data Index: 1566962 (Python Code)

Max Activating Token Index: 855

Text #16

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2620. Min Act: -0.0002

Data Index: 1568864 (Python Code)

Max Activating Token Index: 77

Text #17

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2632. Min Act: -0.0002

Data Index: 1483024 (Python Code)

Max Activating Token Index: 551

Text #18

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2342. Min Act: -0.0002

Data Index: 1645718 (Python Code)

Max Activating Token Index: 955

Text #19

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2487. Min Act: -0.0002

Data Index: 1362555 (Python Code)

Max Activating Token Index: 946