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

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

Neuron 111 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0318. Min Range: -3.0318

Max Act: 2.9804. Min Act: -0.0001

Data Index: 1508669 (Python Code)

Max Activating Token Index: 145

Text #1

Max Range: 3.0318. Min Range: -3.0318

Max Act: 3.0318. Min Act: -0.0000

Data Index: 1495181 (Python Code)

Max Activating Token Index: 543

Text #2

Max Range: 3.0318. Min Range: -3.0318

Max Act: 2.7252. Min Act: -0.0001

Data Index: 1630728 (Python Code)

Max Activating Token Index: 314

Text #3

Max Range: 3.0318. Min Range: -3.0318

Max Act: 3.0186. Min Act: -0.0000

Data Index: 1393964 (Python Code)

Max Activating Token Index: 795

Text #4

Max Range: 3.0318. Min Range: -3.0318

Max Act: 2.9711. Min Act: -0.0001

Data Index: 1205986 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 3.0318. Min Range: -3.0318

Max Act: 2.6628. Min Act: -0.0000

Data Index: 1630653 (Python Code)

Max Activating Token Index: 901

Text #6

Max Range: 3.0318. Min Range: -3.0318

Max Act: 2.6378. Min Act: -0.0000

Data Index: 1629182 (Python Code)

Max Activating Token Index: 960

Text #7

Max Range: 3.0318. Min Range: -3.0318

Max Act: 2.8801. Min Act: -0.0000

Data Index: 1617315 (Python Code)

Max Activating Token Index: 570

Text #8

Max Range: 3.0318. Min Range: -3.0318

Max Act: 2.7194. Min Act: -0.0000

Data Index: 1618539 (Python Code)

Max Activating Token Index: 112

Text #9

Max Range: 3.0318. Min Range: -3.0318

Max Act: 2.9026. Min Act: -0.0000

Data Index: 1444411 (Python Code)

Max Activating Token Index: 744

Text #10

Max Range: 3.0318. Min Range: -3.0318

Max Act: 2.6374. Min Act: -0.0001

Data Index: 825929 (C4 (Web Text))

Max Activating Token Index: 898

Text #11

Max Range: 3.0318. Min Range: -3.0318

Max Act: 2.2935. Min Act: -0.0001

Data Index: 662857 (C4 (Web Text))

Max Activating Token Index: 918

Text #12

Max Range: 3.0318. Min Range: -3.0318

Max Act: 2.3746. Min Act: -0.0000

Data Index: 367936 (C4 (Web Text))

Max Activating Token Index: 712

Text #13

Max Range: 3.0318. Min Range: -3.0318

Max Act: 2.4488. Min Act: -0.0001

Data Index: 39926 (C4 (Web Text))

Max Activating Token Index: 677

Text #14

Max Range: 3.0318. Min Range: -3.0318

Max Act: 2.1872. Min Act: -0.0001

Data Index: 1070705 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 3.0318. Min Range: -3.0318

Max Act: 2.2088. Min Act: -0.0000

Data Index: 766007 (C4 (Web Text))

Max Activating Token Index: 680

Text #16

Max Range: 3.0318. Min Range: -3.0318

Max Act: 2.0903. Min Act: -0.0001

Data Index: 545600 (C4 (Web Text))

Max Activating Token Index: 564

Text #17

Max Range: 3.0318. Min Range: -3.0318

Max Act: 2.0453. Min Act: -0.0000

Data Index: 1636737 (Python Code)

Max Activating Token Index: 481

Text #18

Max Range: 3.0318. Min Range: -3.0318

Max Act: 1.9176. Min Act: -0.0000

Data Index: 542603 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 3.0318. Min Range: -3.0318

Max Act: 2.0675. Min Act: -0.0001

Data Index: 546915 (C4 (Web Text))

Max Activating Token Index: 955