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

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

Neuron 5906 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: 6.3547. Min Range: -6.3547

Max Act: 6.3547. Min Act: -0.0000

Data Index: 375969 (C4 (Web Text))

Max Activating Token Index: 933

Text #1

Max Range: 6.3547. Min Range: -6.3547

Max Act: 4.7199. Min Act: -0.0000

Data Index: 1605412 (Python Code)

Max Activating Token Index: 789

Text #2

Max Range: 6.3547. Min Range: -6.3547

Max Act: 4.6233. Min Act: -0.0000

Data Index: 1652612 (Python Code)

Max Activating Token Index: 333

Text #3

Max Range: 6.3547. Min Range: -6.3547

Max Act: 4.0129. Min Act: -0.0000

Data Index: 1470756 (Python Code)

Max Activating Token Index: 797

Text #4

Max Range: 6.3547. Min Range: -6.3547

Max Act: 4.0164. Min Act: -0.0000

Data Index: 1540396 (Python Code)

Max Activating Token Index: 504

Text #5

Max Range: 6.3547. Min Range: -6.3547

Max Act: 4.1235. Min Act: -0.0000

Data Index: 1443143 (Python Code)

Max Activating Token Index: 177

Text #6

Max Range: 6.3547. Min Range: -6.3547

Max Act: 3.6577. Min Act: -0.0000

Data Index: 1587396 (Python Code)

Max Activating Token Index: 964

Text #7

Max Range: 6.3547. Min Range: -6.3547

Max Act: 4.1718. Min Act: -0.0000

Data Index: 1467950 (Python Code)

Max Activating Token Index: 339

Text #8

Max Range: 6.3547. Min Range: -6.3547

Max Act: 3.8769. Min Act: -0.0000

Data Index: 1655631 (Python Code)

Max Activating Token Index: 747

Text #9

Max Range: 6.3547. Min Range: -6.3547

Max Act: 3.3932. Min Act: -0.0000

Data Index: 1442197 (Python Code)

Max Activating Token Index: 937

Text #10

Max Range: 6.3547. Min Range: -6.3547

Max Act: 3.3648. Min Act: -0.0000

Data Index: 1374968 (Python Code)

Max Activating Token Index: 309

Text #11

Max Range: 6.3547. Min Range: -6.3547

Max Act: 3.7900. Min Act: -0.0000

Data Index: 1604558 (Python Code)

Max Activating Token Index: 697

Text #12

Max Range: 6.3547. Min Range: -6.3547

Max Act: 3.8214. Min Act: -0.0000

Data Index: 1655263 (Python Code)

Max Activating Token Index: 937

Text #13

Max Range: 6.3547. Min Range: -6.3547

Max Act: 3.8528. Min Act: -0.0000

Data Index: 1549910 (Python Code)

Max Activating Token Index: 774

Text #14

Max Range: 6.3547. Min Range: -6.3547

Max Act: 4.2424. Min Act: -0.0000

Data Index: 1439625 (Python Code)

Max Activating Token Index: 874

Text #15

Max Range: 6.3547. Min Range: -6.3547

Max Act: 3.8682. Min Act: -0.0000

Data Index: 1491966 (Python Code)

Max Activating Token Index: 607

Text #16

Max Range: 6.3547. Min Range: -6.3547

Max Act: 4.0284. Min Act: -0.0000

Data Index: 1506063 (Python Code)

Max Activating Token Index: 848

Text #17

Max Range: 6.3547. Min Range: -6.3547

Max Act: 3.8297. Min Act: -0.0000

Data Index: 1498825 (Python Code)

Max Activating Token Index: 519

Text #18

Max Range: 6.3547. Min Range: -6.3547

Max Act: 3.5310. Min Act: -0.0000

Data Index: 1605103 (Python Code)

Max Activating Token Index: 904

Text #19

Max Range: 6.3547. Min Range: -6.3547

Max Act: 3.6439. Min Act: -0.0000

Data Index: 1444906 (Python Code)

Max Activating Token Index: 609