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

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

Neuron 3402 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6880. Min Range: -3.6880

Max Act: 3.5785. Min Act: -0.0000

Data Index: 1569314 (Python Code)

Max Activating Token Index: 58

Text #1

Max Range: 3.6880. Min Range: -3.6880

Max Act: 3.6880. Min Act: -0.0000

Data Index: 1522260 (Python Code)

Max Activating Token Index: 115

Text #2

Max Range: 3.6880. Min Range: -3.6880

Max Act: 3.3652. Min Act: -0.0000

Data Index: 1575088 (Python Code)

Max Activating Token Index: 38

Text #3

Max Range: 3.6880. Min Range: -3.6880

Max Act: 3.2427. Min Act: -0.0000

Data Index: 1593098 (Python Code)

Max Activating Token Index: 68

Text #4

Max Range: 3.6880. Min Range: -3.6880

Max Act: 2.6125. Min Act: -0.0000

Data Index: 1584714 (Python Code)

Max Activating Token Index: 160

Text #5

Max Range: 3.6880. Min Range: -3.6880

Max Act: 2.5855. Min Act: -0.0000

Data Index: 1542834 (Python Code)

Max Activating Token Index: 140

Text #6

Max Range: 3.6880. Min Range: -3.6880

Max Act: 2.6328. Min Act: -0.0000

Data Index: 1615178 (Python Code)

Max Activating Token Index: 768

Text #7

Max Range: 3.6880. Min Range: -3.6880

Max Act: 2.5760. Min Act: -0.0000

Data Index: 1439140 (Python Code)

Max Activating Token Index: 345

Text #8

Max Range: 3.6880. Min Range: -3.6880

Max Act: 2.3291. Min Act: -0.0000

Data Index: 1538405 (Python Code)

Max Activating Token Index: 917

Text #9

Max Range: 3.6880. Min Range: -3.6880

Max Act: 2.3858. Min Act: -0.0000

Data Index: 1647334 (Python Code)

Max Activating Token Index: 1018

Text #10

Max Range: 3.6880. Min Range: -3.6880

Max Act: 2.2098. Min Act: -0.0000

Data Index: 1586639 (Python Code)

Max Activating Token Index: 574

Text #11

Max Range: 3.6880. Min Range: -3.6880

Max Act: 2.1851. Min Act: -0.0000

Data Index: 1596002 (Python Code)

Max Activating Token Index: 718

Text #12

Max Range: 3.6880. Min Range: -3.6880

Max Act: 2.2793. Min Act: -0.0000

Data Index: 1572975 (Python Code)

Max Activating Token Index: 975

Text #13

Max Range: 3.6880. Min Range: -3.6880

Max Act: 2.3360. Min Act: -0.0000

Data Index: 1538902 (Python Code)

Max Activating Token Index: 202

Text #14

Max Range: 3.6880. Min Range: -3.6880

Max Act: 1.9505. Min Act: -0.0000

Data Index: 1509608 (Python Code)

Max Activating Token Index: 884

Text #15

Max Range: 3.6880. Min Range: -3.6880

Max Act: 2.0535. Min Act: -0.0000

Data Index: 1377516 (Python Code)

Max Activating Token Index: 114

Text #16

Max Range: 3.6880. Min Range: -3.6880

Max Act: 2.1588. Min Act: -0.0000

Data Index: 1577624 (Python Code)

Max Activating Token Index: 432

Text #17

Max Range: 3.6880. Min Range: -3.6880

Max Act: 2.1315. Min Act: -0.0000

Data Index: 1389115 (Python Code)

Max Activating Token Index: 100

Text #18

Max Range: 3.6880. Min Range: -3.6880

Max Act: 2.1211. Min Act: -0.0000

Data Index: 1440367 (Python Code)

Max Activating Token Index: 449

Text #19

Max Range: 3.6880. Min Range: -3.6880

Max Act: 2.2581. Min Act: -0.0000

Data Index: 1644374 (Python Code)

Max Activating Token Index: 266