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

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

Neuron 2071 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: 0.0671. Min Range: -0.0671

Max Act: 0.0671. Min Act: -0.0002

Data Index: 774305 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0633. Min Act: -0.0002

Data Index: 1056980 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0617. Min Act: -0.0002

Data Index: 202620 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0570. Min Act: -0.0002

Data Index: 1618036 (Python Code)

Max Activating Token Index: 621

Text #4

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0513. Min Act: -0.0002

Data Index: 1044905 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0477. Min Act: -0.0002

Data Index: 543592 (C4 (Web Text))

Max Activating Token Index: 519

Text #6

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0472. Min Act: -0.0002

Data Index: 1640326 (Python Code)

Max Activating Token Index: 590

Text #7

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0449. Min Act: -0.0002

Data Index: 636992 (C4 (Web Text))

Max Activating Token Index: 892

Text #8

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0451. Min Act: -0.0002

Data Index: 146496 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0427. Min Act: -0.0002

Data Index: 1018970 (C4 (Web Text))

Max Activating Token Index: 327

Text #10

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0441. Min Act: -0.0002

Data Index: 1540244 (Python Code)

Max Activating Token Index: 410

Text #11

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0416. Min Act: -0.0002

Data Index: 413145 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0429. Min Act: -0.0002

Data Index: 1140955 (C4 (Web Text))

Max Activating Token Index: 199

Text #13

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0413. Min Act: -0.0002

Data Index: 918932 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0446. Min Act: -0.0002

Data Index: 401207 (C4 (Web Text))

Max Activating Token Index: 348

Text #15

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0423. Min Act: -0.0002

Data Index: 965689 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0405. Min Act: -0.0002

Data Index: 1179983 (C4 (Web Text))

Max Activating Token Index: 842

Text #17

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0389. Min Act: -0.0002

Data Index: 434257 (C4 (Web Text))

Max Activating Token Index: 708

Text #18

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0399. Min Act: -0.0002

Data Index: 175901 (C4 (Web Text))

Max Activating Token Index: 423

Text #19

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0387. Min Act: -0.0002

Data Index: 777314 (C4 (Web Text))

Max Activating Token Index: 757