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

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

Neuron 591 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: 0.0704. Min Range: -0.0704

Max Act: 0.0704. Min Act: -0.0002

Data Index: 154680 (C4 (Web Text))

Max Activating Token Index: 264

Text #1

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0693. Min Act: -0.0002

Data Index: 1505291 (Python Code)

Max Activating Token Index: 476

Text #2

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0624. Min Act: -0.0002

Data Index: 1477412 (Python Code)

Max Activating Token Index: 564

Text #3

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0623. Min Act: 0.0000

Data Index: 1521241 (Python Code)

Max Activating Token Index: 304

Text #4

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0622. Min Act: -0.0002

Data Index: 1510489 (Python Code)

Max Activating Token Index: 874

Text #5

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0601. Min Act: -0.0001

Data Index: 1549749 (Python Code)

Max Activating Token Index: 102

Text #6

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0605. Min Act: -0.0001

Data Index: 1552169 (Python Code)

Max Activating Token Index: 243

Text #7

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0605. Min Act: -0.0002

Data Index: 269100 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0599. Min Act: -0.0001

Data Index: 1526017 (Python Code)

Max Activating Token Index: 71

Text #9

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0592. Min Act: -0.0002

Data Index: 618057 (C4 (Web Text))

Max Activating Token Index: 294

Text #10

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0600. Min Act: -0.0002

Data Index: 1488939 (Python Code)

Max Activating Token Index: 779

Text #11

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0590. Min Act: -0.0001

Data Index: 1641800 (Python Code)

Max Activating Token Index: 203

Text #12

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0586. Min Act: 0.0002

Data Index: 1409973 (Python Code)

Max Activating Token Index: 592

Text #13

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0614. Min Act: -0.0002

Data Index: 1368036 (Python Code)

Max Activating Token Index: 733

Text #14

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0593. Min Act: -0.0002

Data Index: 1486101 (Python Code)

Max Activating Token Index: 110

Text #15

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0571. Min Act: -0.0001

Data Index: 749523 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0571. Min Act: 0.0003

Data Index: 1544521 (Python Code)

Max Activating Token Index: 471

Text #17

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0575. Min Act: -0.0002

Data Index: 1439981 (Python Code)

Max Activating Token Index: 38

Text #18

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0598. Min Act: -0.0002

Data Index: 1217513 (C4 (Web Text))

Max Activating Token Index: 316

Text #19

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0568. Min Act: -0.0002

Data Index: 1474143 (Python Code)

Max Activating Token Index: 432