Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6136 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.7357. Min Range: -5.7357

Max Act: 5.7357. Min Act: -0.0002

Data Index: 837129 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 5.7357. Min Range: -5.7357

Max Act: 4.7104. Min Act: -0.0002

Data Index: 1591930 (Python Code)

Max Activating Token Index: 896

Text #2

Max Range: 5.7357. Min Range: -5.7357

Max Act: 2.6879. Min Act: -0.0002

Data Index: 659080 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 5.7357. Min Range: -5.7357

Max Act: 2.9516. Min Act: -0.0002

Data Index: 1121134 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 5.7357. Min Range: -5.7357

Max Act: 2.9639. Min Act: -0.0002

Data Index: 1529385 (Python Code)

Max Activating Token Index: 889

Text #5

Max Range: 5.7357. Min Range: -5.7357

Max Act: 1.8778. Min Act: -0.0002

Data Index: 807900 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 5.7357. Min Range: -5.7357

Max Act: 2.2425. Min Act: -0.0002

Data Index: 1428222 (Python Code)

Max Activating Token Index: 614

Text #7

Max Range: 5.7357. Min Range: -5.7357

Max Act: 1.8904. Min Act: -0.0002

Data Index: 1592119 (Python Code)

Max Activating Token Index: 645

Text #8

Max Range: 5.7357. Min Range: -5.7357

Max Act: 1.7197. Min Act: -0.0002

Data Index: 741234 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 5.7357. Min Range: -5.7357

Max Act: 1.6822. Min Act: -0.0002

Data Index: 1322862 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 5.7357. Min Range: -5.7357

Max Act: 1.5042. Min Act: -0.0002

Data Index: 1233715 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 5.7357. Min Range: -5.7357

Max Act: 1.1381. Min Act: -0.0002

Data Index: 607280 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 5.7357. Min Range: -5.7357

Max Act: 1.1661. Min Act: -0.0002

Data Index: 950698 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 5.7357. Min Range: -5.7357

Max Act: 1.0758. Min Act: -0.0002

Data Index: 1560512 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 5.7357. Min Range: -5.7357

Max Act: 1.0616. Min Act: -0.0002

Data Index: 940843 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 5.7357. Min Range: -5.7357

Max Act: 1.0983. Min Act: -0.0002

Data Index: 555893 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 5.7357. Min Range: -5.7357

Max Act: 0.8667. Min Act: -0.0002

Data Index: 840380 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 5.7357. Min Range: -5.7357

Max Act: 0.8270. Min Act: -0.0002

Data Index: 635401 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 5.7357. Min Range: -5.7357

Max Act: 0.8805. Min Act: -0.0002

Data Index: 1568588 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 5.7357. Min Range: -5.7357

Max Act: 0.7192. Min Act: -0.0002

Data Index: 1608714 (Python Code)

Max Activating Token Index: 1023