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

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

Neuron 4914 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: 3.7954. Min Range: -3.7954

Max Act: 3.7954. Min Act: -0.0001

Data Index: 1606872 (Python Code)

Max Activating Token Index: 428

Text #1

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.7876. Min Act: -0.0001

Data Index: 1479979 (Python Code)

Max Activating Token Index: 761

Text #2

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.4091. Min Act: -0.0001

Data Index: 1620127 (Python Code)

Max Activating Token Index: 285

Text #3

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.4299. Min Act: -0.0001

Data Index: 1655950 (Python Code)

Max Activating Token Index: 911

Text #4

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.3543. Min Act: -0.0001

Data Index: 1595888 (Python Code)

Max Activating Token Index: 628

Text #5

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.3840. Min Act: -0.0001

Data Index: 1628527 (Python Code)

Max Activating Token Index: 194

Text #6

Max Range: 3.7954. Min Range: -3.7954

Max Act: 2.9308. Min Act: -0.0001

Data Index: 1362259 (Python Code)

Max Activating Token Index: 662

Text #7

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.2691. Min Act: -0.0001

Data Index: 1454113 (Python Code)

Max Activating Token Index: 314

Text #8

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.4714. Min Act: -0.0001

Data Index: 1498550 (Python Code)

Max Activating Token Index: 884

Text #9

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.0132. Min Act: -0.0001

Data Index: 1654700 (Python Code)

Max Activating Token Index: 616

Text #10

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.2898. Min Act: -0.0001

Data Index: 1293030 (C4 (Web Text))

Max Activating Token Index: 652

Text #11

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.2370. Min Act: -0.0001

Data Index: 1572640 (Python Code)

Max Activating Token Index: 769

Text #12

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.0476. Min Act: -0.0001

Data Index: 1416293 (Python Code)

Max Activating Token Index: 732

Text #13

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.1783. Min Act: -0.0001

Data Index: 1541951 (Python Code)

Max Activating Token Index: 962

Text #14

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.1731. Min Act: -0.0001

Data Index: 1514282 (Python Code)

Max Activating Token Index: 717

Text #15

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.1674. Min Act: -0.0001

Data Index: 1435884 (Python Code)

Max Activating Token Index: 51

Text #16

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.1807. Min Act: -0.0001

Data Index: 1504546 (Python Code)

Max Activating Token Index: 565

Text #17

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.0002. Min Act: -0.0001

Data Index: 1428587 (Python Code)

Max Activating Token Index: 292

Text #18

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.2639. Min Act: -0.0001

Data Index: 1363579 (Python Code)

Max Activating Token Index: 217

Text #19

Max Range: 3.7954. Min Range: -3.7954

Max Act: 2.9708. Min Act: -0.0001

Data Index: 1403184 (Python Code)

Max Activating Token Index: 115