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

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

Neuron 5514 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.3745. Min Act: -0.0000

Data Index: 1431361 (Python Code)

Max Activating Token Index: 530

Text #1

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.3213. Min Act: -0.0000

Data Index: 1635110 (Python Code)

Max Activating Token Index: 570

Text #2

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.3196. Min Act: -0.0000

Data Index: 1471497 (Python Code)

Max Activating Token Index: 54

Text #3

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2993. Min Act: -0.0000

Data Index: 1426464 (Python Code)

Max Activating Token Index: 998

Text #4

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2796. Min Act: -0.0000

Data Index: 384612 (C4 (Web Text))

Max Activating Token Index: 282

Text #5

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2778. Min Act: -0.0000

Data Index: 1401818 (Python Code)

Max Activating Token Index: 685

Text #6

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2670. Min Act: -0.0000

Data Index: 1434183 (Python Code)

Max Activating Token Index: 119

Text #7

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2558. Min Act: -0.0000

Data Index: 1423503 (Python Code)

Max Activating Token Index: 829

Text #8

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2732. Min Act: -0.0000

Data Index: 1372931 (Python Code)

Max Activating Token Index: 339

Text #9

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2599. Min Act: -0.0000

Data Index: 1583503 (Python Code)

Max Activating Token Index: 849

Text #10

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2471. Min Act: -0.0000

Data Index: 1618269 (Python Code)

Max Activating Token Index: 310

Text #11

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2739. Min Act: -0.0000

Data Index: 1380714 (Python Code)

Max Activating Token Index: 498

Text #12

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2658. Min Act: -0.0000

Data Index: 1593126 (Python Code)

Max Activating Token Index: 736

Text #13

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2621. Min Act: -0.0000

Data Index: 606666 (C4 (Web Text))

Max Activating Token Index: 296

Text #14

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2405. Min Act: -0.0000

Data Index: 1556368 (Python Code)

Max Activating Token Index: 894

Text #15

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2604. Min Act: -0.0000

Data Index: 1390509 (Python Code)

Max Activating Token Index: 391

Text #16

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2404. Min Act: -0.0000

Data Index: 1533304 (Python Code)

Max Activating Token Index: 743

Text #17

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2520. Min Act: -0.0000

Data Index: 1439989 (Python Code)

Max Activating Token Index: 449

Text #18

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2414. Min Act: -0.0000

Data Index: 1625282 (Python Code)

Max Activating Token Index: 247

Text #19

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2522. Min Act: -0.0000

Data Index: 366117 (C4 (Web Text))

Max Activating Token Index: 443