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

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

Neuron 5548 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8776. Min Range: -1.8776

Max Act: 1.8776. Min Act: -0.0000

Data Index: 1557294 (Python Code)

Max Activating Token Index: 468

Text #1

Max Range: 1.8776. Min Range: -1.8776

Max Act: 1.7915. Min Act: -0.0000

Data Index: 1562098 (Python Code)

Max Activating Token Index: 246

Text #2

Max Range: 1.8776. Min Range: -1.8776

Max Act: 1.8247. Min Act: -0.0000

Data Index: 1558602 (Python Code)

Max Activating Token Index: 866

Text #3

Max Range: 1.8776. Min Range: -1.8776

Max Act: 1.6492. Min Act: -0.0000

Data Index: 1596170 (Python Code)

Max Activating Token Index: 51

Text #4

Max Range: 1.8776. Min Range: -1.8776

Max Act: 1.4476. Min Act: -0.0000

Data Index: 1448140 (Python Code)

Max Activating Token Index: 845

Text #5

Max Range: 1.8776. Min Range: -1.8776

Max Act: 1.3402. Min Act: -0.0000

Data Index: 1646583 (Python Code)

Max Activating Token Index: 274

Text #6

Max Range: 1.8776. Min Range: -1.8776

Max Act: 1.3988. Min Act: -0.0000

Data Index: 1578714 (Python Code)

Max Activating Token Index: 122

Text #7

Max Range: 1.8776. Min Range: -1.8776

Max Act: 1.3751. Min Act: -0.0000

Data Index: 1629579 (Python Code)

Max Activating Token Index: 268

Text #8

Max Range: 1.8776. Min Range: -1.8776

Max Act: 1.3829. Min Act: -0.0000

Data Index: 1474559 (Python Code)

Max Activating Token Index: 35

Text #9

Max Range: 1.8776. Min Range: -1.8776

Max Act: 1.4548. Min Act: -0.0000

Data Index: 1414314 (Python Code)

Max Activating Token Index: 247

Text #10

Max Range: 1.8776. Min Range: -1.8776

Max Act: 1.4467. Min Act: -0.0000

Data Index: 1467582 (Python Code)

Max Activating Token Index: 128

Text #11

Max Range: 1.8776. Min Range: -1.8776

Max Act: 1.3598. Min Act: -0.0000

Data Index: 1494794 (Python Code)

Max Activating Token Index: 15

Text #12

Max Range: 1.8776. Min Range: -1.8776

Max Act: 1.2951. Min Act: -0.0000

Data Index: 1470367 (Python Code)

Max Activating Token Index: 536

Text #13

Max Range: 1.8776. Min Range: -1.8776

Max Act: 1.1948. Min Act: -0.0000

Data Index: 1534875 (Python Code)

Max Activating Token Index: 177

Text #14

Max Range: 1.8776. Min Range: -1.8776

Max Act: 1.3514. Min Act: -0.0000

Data Index: 1453819 (Python Code)

Max Activating Token Index: 4

Text #15

Max Range: 1.8776. Min Range: -1.8776

Max Act: 1.2315. Min Act: -0.0000

Data Index: 1410846 (Python Code)

Max Activating Token Index: 326

Text #16

Max Range: 1.8776. Min Range: -1.8776

Max Act: 1.3762. Min Act: -0.0000

Data Index: 1597007 (Python Code)

Max Activating Token Index: 96

Text #17

Max Range: 1.8776. Min Range: -1.8776

Max Act: 1.2220. Min Act: -0.0000

Data Index: 1614052 (Python Code)

Max Activating Token Index: 23

Text #18

Max Range: 1.8776. Min Range: -1.8776

Max Act: 1.3360. Min Act: -0.0000

Data Index: 1371081 (Python Code)

Max Activating Token Index: 789

Text #19

Max Range: 1.8776. Min Range: -1.8776

Max Act: 1.2417. Min Act: -0.0000

Data Index: 1430095 (Python Code)

Max Activating Token Index: 78