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

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

Neuron 2095 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6309. Min Range: -3.6309

Max Act: 3.6309. Min Act: -0.0000

Data Index: 1635533 (Python Code)

Max Activating Token Index: 292

Text #1

Max Range: 3.6309. Min Range: -3.6309

Max Act: 3.4449. Min Act: -0.0000

Data Index: 1597608 (Python Code)

Max Activating Token Index: 998

Text #2

Max Range: 3.6309. Min Range: -3.6309

Max Act: 2.9789. Min Act: -0.0000

Data Index: 1626318 (Python Code)

Max Activating Token Index: 923

Text #3

Max Range: 3.6309. Min Range: -3.6309

Max Act: 2.6229. Min Act: -0.0000

Data Index: 1614052 (Python Code)

Max Activating Token Index: 940

Text #4

Max Range: 3.6309. Min Range: -3.6309

Max Act: 2.7804. Min Act: -0.0000

Data Index: 1444745 (Python Code)

Max Activating Token Index: 746

Text #5

Max Range: 3.6309. Min Range: -3.6309

Max Act: 2.7734. Min Act: -0.0000

Data Index: 1545216 (Python Code)

Max Activating Token Index: 733

Text #6

Max Range: 3.6309. Min Range: -3.6309

Max Act: 2.5508. Min Act: -0.0000

Data Index: 1587405 (Python Code)

Max Activating Token Index: 890

Text #7

Max Range: 3.6309. Min Range: -3.6309

Max Act: 2.4811. Min Act: -0.0000

Data Index: 1517046 (Python Code)

Max Activating Token Index: 511

Text #8

Max Range: 3.6309. Min Range: -3.6309

Max Act: 2.2528. Min Act: -0.0000

Data Index: 1422318 (Python Code)

Max Activating Token Index: 557

Text #9

Max Range: 3.6309. Min Range: -3.6309

Max Act: 1.9933. Min Act: -0.0000

Data Index: 1519647 (Python Code)

Max Activating Token Index: 984

Text #10

Max Range: 3.6309. Min Range: -3.6309

Max Act: 2.1892. Min Act: -0.0000

Data Index: 1434486 (Python Code)

Max Activating Token Index: 886

Text #11

Max Range: 3.6309. Min Range: -3.6309

Max Act: 2.0291. Min Act: -0.0000

Data Index: 1389378 (Python Code)

Max Activating Token Index: 815

Text #12

Max Range: 3.6309. Min Range: -3.6309

Max Act: 2.2504. Min Act: -0.0000

Data Index: 1544405 (Python Code)

Max Activating Token Index: 612

Text #13

Max Range: 3.6309. Min Range: -3.6309

Max Act: 2.0450. Min Act: -0.0000

Data Index: 1547747 (Python Code)

Max Activating Token Index: 569

Text #14

Max Range: 3.6309. Min Range: -3.6309

Max Act: 2.0386. Min Act: -0.0000

Data Index: 1398414 (Python Code)

Max Activating Token Index: 664

Text #15

Max Range: 3.6309. Min Range: -3.6309

Max Act: 1.9269. Min Act: -0.0000

Data Index: 1390978 (Python Code)

Max Activating Token Index: 644

Text #16

Max Range: 3.6309. Min Range: -3.6309

Max Act: 1.9124. Min Act: -0.0000

Data Index: 1422030 (Python Code)

Max Activating Token Index: 94

Text #17

Max Range: 3.6309. Min Range: -3.6309

Max Act: 1.8956. Min Act: -0.0000

Data Index: 1385971 (Python Code)

Max Activating Token Index: 761

Text #18

Max Range: 3.6309. Min Range: -3.6309

Max Act: 1.7659. Min Act: -0.0000

Data Index: 1585948 (Python Code)

Max Activating Token Index: 885

Text #19

Max Range: 3.6309. Min Range: -3.6309

Max Act: 2.0931. Min Act: -0.0000

Data Index: 1584733 (Python Code)

Max Activating Token Index: 145