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

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

Neuron 1086 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: 0.0943. Min Range: -0.0943

Max Act: 0.0943. Min Act: -0.0002

Data Index: 1590088 (Python Code)

Max Activating Token Index: 880

Text #1

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0943. Min Act: -0.0002

Data Index: 1407479 (Python Code)

Max Activating Token Index: 255

Text #2

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0831. Min Act: -0.0002

Data Index: 1447741 (Python Code)

Max Activating Token Index: 686

Text #3

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0903. Min Act: -0.0002

Data Index: 1457076 (Python Code)

Max Activating Token Index: 147

Text #4

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0885. Min Act: -0.0002

Data Index: 1559550 (Python Code)

Max Activating Token Index: 154

Text #5

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0854. Min Act: -0.0002

Data Index: 1616549 (Python Code)

Max Activating Token Index: 57

Text #6

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0861. Min Act: -0.0002

Data Index: 1629324 (Python Code)

Max Activating Token Index: 60

Text #7

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0806. Min Act: -0.0002

Data Index: 1555876 (Python Code)

Max Activating Token Index: 313

Text #8

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0795. Min Act: -0.0002

Data Index: 1485856 (Python Code)

Max Activating Token Index: 178

Text #9

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0824. Min Act: -0.0002

Data Index: 1398054 (Python Code)

Max Activating Token Index: 271

Text #10

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0833. Min Act: -0.0002

Data Index: 1601334 (Python Code)

Max Activating Token Index: 375

Text #11

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0810. Min Act: -0.0002

Data Index: 1536801 (Python Code)

Max Activating Token Index: 477

Text #12

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0816. Min Act: -0.0002

Data Index: 1464586 (Python Code)

Max Activating Token Index: 411

Text #13

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0825. Min Act: -0.0002

Data Index: 1445393 (Python Code)

Max Activating Token Index: 145

Text #14

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0823. Min Act: -0.0002

Data Index: 1411593 (Python Code)

Max Activating Token Index: 709

Text #15

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0832. Min Act: -0.0002

Data Index: 1517794 (Python Code)

Max Activating Token Index: 293

Text #16

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0880. Min Act: -0.0002

Data Index: 1457536 (Python Code)

Max Activating Token Index: 510

Text #17

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0807. Min Act: -0.0002

Data Index: 1434458 (Python Code)

Max Activating Token Index: 54

Text #18

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0822. Min Act: -0.0002

Data Index: 1414004 (Python Code)

Max Activating Token Index: 544

Text #19

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0787. Min Act: -0.0002

Data Index: 1580042 (Python Code)

Max Activating Token Index: 367