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

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

Neuron 5711 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: 1.2745. Min Range: -1.2745

Max Act: 1.2745. Min Act: -0.0000

Data Index: 938015 (C4 (Web Text))

Max Activating Token Index: 402

Text #1

Max Range: 1.2745. Min Range: -1.2745

Max Act: 1.0001. Min Act: -0.0000

Data Index: 539448 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 1.2745. Min Range: -1.2745

Max Act: 1.0017. Min Act: -0.0000

Data Index: 10654 (C4 (Web Text))

Max Activating Token Index: 268

Text #3

Max Range: 1.2745. Min Range: -1.2745

Max Act: 0.8492. Min Act: -0.0000

Data Index: 171547 (C4 (Web Text))

Max Activating Token Index: 475

Text #4

Max Range: 1.2745. Min Range: -1.2745

Max Act: 0.8062. Min Act: -0.0000

Data Index: 1595300 (Python Code)

Max Activating Token Index: 848

Text #5

Max Range: 1.2745. Min Range: -1.2745

Max Act: 0.8393. Min Act: -0.0000

Data Index: 1557677 (Python Code)

Max Activating Token Index: 422

Text #6

Max Range: 1.2745. Min Range: -1.2745

Max Act: 0.7909. Min Act: -0.0000

Data Index: 1415345 (Python Code)

Max Activating Token Index: 998

Text #7

Max Range: 1.2745. Min Range: -1.2745

Max Act: 0.8308. Min Act: -0.0000

Data Index: 1058606 (C4 (Web Text))

Max Activating Token Index: 329

Text #8

Max Range: 1.2745. Min Range: -1.2745

Max Act: 0.7595. Min Act: -0.0000

Data Index: 90501 (C4 (Web Text))

Max Activating Token Index: 567

Text #9

Max Range: 1.2745. Min Range: -1.2745

Max Act: 0.7505. Min Act: -0.0000

Data Index: 1384023 (Python Code)

Max Activating Token Index: 244

Text #10

Max Range: 1.2745. Min Range: -1.2745

Max Act: 0.7312. Min Act: -0.0000

Data Index: 657693 (C4 (Web Text))

Max Activating Token Index: 908

Text #11

Max Range: 1.2745. Min Range: -1.2745

Max Act: 0.7203. Min Act: -0.0000

Data Index: 473177 (C4 (Web Text))

Max Activating Token Index: 406

Text #12

Max Range: 1.2745. Min Range: -1.2745

Max Act: 0.7183. Min Act: -0.0000

Data Index: 166890 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 1.2745. Min Range: -1.2745

Max Act: 0.6895. Min Act: -0.0000

Data Index: 1603162 (Python Code)

Max Activating Token Index: 547

Text #14

Max Range: 1.2745. Min Range: -1.2745

Max Act: 0.7254. Min Act: -0.0000

Data Index: 1557933 (Python Code)

Max Activating Token Index: 996

Text #15

Max Range: 1.2745. Min Range: -1.2745

Max Act: 0.6787. Min Act: -0.0000

Data Index: 23421 (C4 (Web Text))

Max Activating Token Index: 265

Text #16

Max Range: 1.2745. Min Range: -1.2745

Max Act: 0.6796. Min Act: -0.0000

Data Index: 1472635 (Python Code)

Max Activating Token Index: 493

Text #17

Max Range: 1.2745. Min Range: -1.2745

Max Act: 0.6156. Min Act: -0.0000

Data Index: 1205020 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 1.2745. Min Range: -1.2745

Max Act: 0.6503. Min Act: -0.0000

Data Index: 1644838 (Python Code)

Max Activating Token Index: 954

Text #19

Max Range: 1.2745. Min Range: -1.2745

Max Act: 0.6976. Min Act: -0.0000

Data Index: 1427741 (Python Code)

Max Activating Token Index: 389