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

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

Neuron 1259 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: 1.1401. Min Range: -1.1401

Max Act: 1.1401. Min Act: -0.0001

Data Index: 223925 (C4 (Web Text))

Max Activating Token Index: 680

Text #1

Max Range: 1.1401. Min Range: -1.1401

Max Act: 1.0400. Min Act: -0.0001

Data Index: 1072645 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 1.1401. Min Range: -1.1401

Max Act: 1.0967. Min Act: -0.0001

Data Index: 57787 (C4 (Web Text))

Max Activating Token Index: 867

Text #3

Max Range: 1.1401. Min Range: -1.1401

Max Act: 1.1054. Min Act: -0.0001

Data Index: 1173356 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.9898. Min Act: -0.0001

Data Index: 885571 (C4 (Web Text))

Max Activating Token Index: 997

Text #5

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.8469. Min Act: -0.0000

Data Index: 442626 (C4 (Web Text))

Max Activating Token Index: 702

Text #6

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.7856. Min Act: -0.0000

Data Index: 54873 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.8664. Min Act: -0.0000

Data Index: 1629706 (Python Code)

Max Activating Token Index: 637

Text #8

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.8069. Min Act: -0.0000

Data Index: 1147463 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.8010. Min Act: -0.0000

Data Index: 1520912 (Python Code)

Max Activating Token Index: 487

Text #10

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.8536. Min Act: -0.0001

Data Index: 614578 (C4 (Web Text))

Max Activating Token Index: 564

Text #11

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.8325. Min Act: -0.0000

Data Index: 1443562 (Python Code)

Max Activating Token Index: 372

Text #12

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.8226. Min Act: -0.0001

Data Index: 239569 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.8200. Min Act: -0.0000

Data Index: 1521366 (Python Code)

Max Activating Token Index: 990

Text #14

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.7886. Min Act: -0.0001

Data Index: 465201 (C4 (Web Text))

Max Activating Token Index: 284

Text #15

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.8596. Min Act: -0.0000

Data Index: 773889 (C4 (Web Text))

Max Activating Token Index: 777

Text #16

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.7672. Min Act: -0.0001

Data Index: 416729 (C4 (Web Text))

Max Activating Token Index: 463

Text #17

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.7833. Min Act: -0.0001

Data Index: 169018 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.7289. Min Act: -0.0000

Data Index: 1371171 (Python Code)

Max Activating Token Index: 114

Text #19

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.7369. Min Act: -0.0001

Data Index: 840102 (C4 (Web Text))

Max Activating Token Index: 688