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

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

Neuron 5461 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8110. Min Range: -3.8110

Max Act: 3.7412. Min Act: -0.0000

Data Index: 1379593 (Python Code)

Max Activating Token Index: 725

Text #1

Max Range: 3.8110. Min Range: -3.8110

Max Act: 3.8110. Min Act: -0.0000

Data Index: 1542130 (Python Code)

Max Activating Token Index: 422

Text #2

Max Range: 3.8110. Min Range: -3.8110

Max Act: 3.4331. Min Act: -0.0000

Data Index: 1650194 (Python Code)

Max Activating Token Index: 889

Text #3

Max Range: 3.8110. Min Range: -3.8110

Max Act: 3.3219. Min Act: -0.0000

Data Index: 1504585 (Python Code)

Max Activating Token Index: 711

Text #4

Max Range: 3.8110. Min Range: -3.8110

Max Act: 3.0997. Min Act: -0.0000

Data Index: 1426159 (Python Code)

Max Activating Token Index: 944

Text #5

Max Range: 3.8110. Min Range: -3.8110

Max Act: 3.0635. Min Act: -0.0000

Data Index: 1475960 (Python Code)

Max Activating Token Index: 917

Text #6

Max Range: 3.8110. Min Range: -3.8110

Max Act: 2.9363. Min Act: -0.0000

Data Index: 1516314 (Python Code)

Max Activating Token Index: 858

Text #7

Max Range: 3.8110. Min Range: -3.8110

Max Act: 2.9685. Min Act: -0.0000

Data Index: 1416707 (Python Code)

Max Activating Token Index: 370

Text #8

Max Range: 3.8110. Min Range: -3.8110

Max Act: 2.6480. Min Act: -0.0000

Data Index: 1443865 (Python Code)

Max Activating Token Index: 486

Text #9

Max Range: 3.8110. Min Range: -3.8110

Max Act: 2.6271. Min Act: -0.0000

Data Index: 1450037 (Python Code)

Max Activating Token Index: 743

Text #10

Max Range: 3.8110. Min Range: -3.8110

Max Act: 2.5406. Min Act: -0.0000

Data Index: 1637075 (Python Code)

Max Activating Token Index: 370

Text #11

Max Range: 3.8110. Min Range: -3.8110

Max Act: 2.6571. Min Act: -0.0000

Data Index: 1409686 (Python Code)

Max Activating Token Index: 33

Text #12

Max Range: 3.8110. Min Range: -3.8110

Max Act: 2.7826. Min Act: -0.0000

Data Index: 487754 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 3.8110. Min Range: -3.8110

Max Act: 2.6463. Min Act: -0.0000

Data Index: 1573134 (Python Code)

Max Activating Token Index: 879

Text #14

Max Range: 3.8110. Min Range: -3.8110

Max Act: 2.5574. Min Act: -0.0000

Data Index: 1410699 (Python Code)

Max Activating Token Index: 390

Text #15

Max Range: 3.8110. Min Range: -3.8110

Max Act: 2.5312. Min Act: -0.0000

Data Index: 1401313 (Python Code)

Max Activating Token Index: 125

Text #16

Max Range: 3.8110. Min Range: -3.8110

Max Act: 2.5113. Min Act: -0.0000

Data Index: 1537788 (Python Code)

Max Activating Token Index: 101

Text #17

Max Range: 3.8110. Min Range: -3.8110

Max Act: 2.5145. Min Act: -0.0000

Data Index: 1574032 (Python Code)

Max Activating Token Index: 887

Text #18

Max Range: 3.8110. Min Range: -3.8110

Max Act: 2.5074. Min Act: -0.0000

Data Index: 1620124 (Python Code)

Max Activating Token Index: 633

Text #19

Max Range: 3.8110. Min Range: -3.8110

Max Act: 2.5047. Min Act: -0.0000

Data Index: 1615873 (Python Code)

Max Activating Token Index: 631