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

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

Neuron 698 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4303. Min Range: -2.4303

Max Act: 2.3741. Min Act: -0.0000

Data Index: 1426034 (Python Code)

Max Activating Token Index: 901

Text #1

Max Range: 2.4303. Min Range: -2.4303

Max Act: 2.2964. Min Act: -0.0000

Data Index: 1607110 (Python Code)

Max Activating Token Index: 872

Text #2

Max Range: 2.4303. Min Range: -2.4303

Max Act: 2.4303. Min Act: -0.0000

Data Index: 1397808 (Python Code)

Max Activating Token Index: 280

Text #3

Max Range: 2.4303. Min Range: -2.4303

Max Act: 2.3171. Min Act: -0.0000

Data Index: 1405010 (Python Code)

Max Activating Token Index: 997

Text #4

Max Range: 2.4303. Min Range: -2.4303

Max Act: 2.1538. Min Act: -0.0000

Data Index: 1489681 (Python Code)

Max Activating Token Index: 98

Text #5

Max Range: 2.4303. Min Range: -2.4303

Max Act: 2.3719. Min Act: -0.0000

Data Index: 1396308 (Python Code)

Max Activating Token Index: 309

Text #6

Max Range: 2.4303. Min Range: -2.4303

Max Act: 2.1532. Min Act: -0.0000

Data Index: 1611951 (Python Code)

Max Activating Token Index: 634

Text #7

Max Range: 2.4303. Min Range: -2.4303

Max Act: 2.0867. Min Act: -0.0000

Data Index: 1500872 (Python Code)

Max Activating Token Index: 139

Text #8

Max Range: 2.4303. Min Range: -2.4303

Max Act: 1.8273. Min Act: -0.0000

Data Index: 1428872 (Python Code)

Max Activating Token Index: 598

Text #9

Max Range: 2.4303. Min Range: -2.4303

Max Act: 1.8848. Min Act: -0.0000

Data Index: 1450235 (Python Code)

Max Activating Token Index: 706

Text #10

Max Range: 2.4303. Min Range: -2.4303

Max Act: 1.8067. Min Act: -0.0000

Data Index: 1378267 (Python Code)

Max Activating Token Index: 673

Text #11

Max Range: 2.4303. Min Range: -2.4303

Max Act: 1.7781. Min Act: -0.0000

Data Index: 1444918 (Python Code)

Max Activating Token Index: 416

Text #12

Max Range: 2.4303. Min Range: -2.4303

Max Act: 1.6316. Min Act: -0.0000

Data Index: 1589890 (Python Code)

Max Activating Token Index: 376

Text #13

Max Range: 2.4303. Min Range: -2.4303

Max Act: 1.9183. Min Act: -0.0000

Data Index: 1640120 (Python Code)

Max Activating Token Index: 891

Text #14

Max Range: 2.4303. Min Range: -2.4303

Max Act: 1.7853. Min Act: -0.0000

Data Index: 1426627 (Python Code)

Max Activating Token Index: 900

Text #15

Max Range: 2.4303. Min Range: -2.4303

Max Act: 1.5156. Min Act: -0.0000

Data Index: 1645343 (Python Code)

Max Activating Token Index: 374

Text #16

Max Range: 2.4303. Min Range: -2.4303

Max Act: 1.9960. Min Act: -0.0000

Data Index: 1539990 (Python Code)

Max Activating Token Index: 371

Text #17

Max Range: 2.4303. Min Range: -2.4303

Max Act: 1.6265. Min Act: -0.0000

Data Index: 1639952 (Python Code)

Max Activating Token Index: 508

Text #18

Max Range: 2.4303. Min Range: -2.4303

Max Act: 1.5878. Min Act: -0.0000

Data Index: 338928 (C4 (Web Text))

Max Activating Token Index: 860

Text #19

Max Range: 2.4303. Min Range: -2.4303

Max Act: 1.5275. Min Act: -0.0000

Data Index: 1496183 (Python Code)

Max Activating Token Index: 1001