Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2280 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.7695. Min Act: -0.0000

Data Index: 1535516 (Python Code)

Max Activating Token Index: 1018

Text #1

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.7712. Min Act: -0.0000

Data Index: 1586027 (Python Code)

Max Activating Token Index: 1019

Text #2

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.7256. Min Act: -0.0000

Data Index: 1513222 (Python Code)

Max Activating Token Index: 898

Text #3

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.7309. Min Act: -0.0000

Data Index: 1406789 (Python Code)

Max Activating Token Index: 945

Text #4

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.7066. Min Act: -0.0001

Data Index: 1547939 (Python Code)

Max Activating Token Index: 217

Text #5

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.7512. Min Act: -0.0001

Data Index: 1561755 (Python Code)

Max Activating Token Index: 1020

Text #6

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.6978. Min Act: -0.0001

Data Index: 1654806 (Python Code)

Max Activating Token Index: 435

Text #7

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.6914. Min Act: -0.0000

Data Index: 1443527 (Python Code)

Max Activating Token Index: 753

Text #8

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.7336. Min Act: -0.0000

Data Index: 1611241 (Python Code)

Max Activating Token Index: 887

Text #9

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.6943. Min Act: -0.0001

Data Index: 1635386 (Python Code)

Max Activating Token Index: 690

Text #10

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.6942. Min Act: -0.0000

Data Index: 1413008 (Python Code)

Max Activating Token Index: 892

Text #11

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.6804. Min Act: -0.0000

Data Index: 1385955 (Python Code)

Max Activating Token Index: 68

Text #12

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.6518. Min Act: -0.0001

Data Index: 1494321 (Python Code)

Max Activating Token Index: 963

Text #13

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.6475. Min Act: -0.0000

Data Index: 1603841 (Python Code)

Max Activating Token Index: 911

Text #14

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.6404. Min Act: -0.0001

Data Index: 1482680 (Python Code)

Max Activating Token Index: 700

Text #15

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.6215. Min Act: -0.0000

Data Index: 1597572 (Python Code)

Max Activating Token Index: 417

Text #16

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.6179. Min Act: -0.0001

Data Index: 1488762 (Python Code)

Max Activating Token Index: 555

Text #17

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.6207. Min Act: -0.0001

Data Index: 1472025 (Python Code)

Max Activating Token Index: 1011

Text #18

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.5982. Min Act: -0.0001

Data Index: 1400781 (Python Code)

Max Activating Token Index: 999

Text #19

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.5586. Min Act: -0.0001

Data Index: 1484380 (Python Code)

Max Activating Token Index: 210