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

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

Neuron 58 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0718. Min Range: -2.0718

Max Act: 2.0324. Min Act: -0.0000

Data Index: 1466441 (Python Code)

Max Activating Token Index: 788

Text #1

Max Range: 2.0718. Min Range: -2.0718

Max Act: 2.0718. Min Act: -0.0000

Data Index: 1626083 (Python Code)

Max Activating Token Index: 128

Text #2

Max Range: 2.0718. Min Range: -2.0718

Max Act: 1.9658. Min Act: -0.0000

Data Index: 1524852 (Python Code)

Max Activating Token Index: 679

Text #3

Max Range: 2.0718. Min Range: -2.0718

Max Act: 1.6958. Min Act: -0.0000

Data Index: 1555413 (Python Code)

Max Activating Token Index: 1007

Text #4

Max Range: 2.0718. Min Range: -2.0718

Max Act: 1.8603. Min Act: -0.0000

Data Index: 1624583 (Python Code)

Max Activating Token Index: 212

Text #5

Max Range: 2.0718. Min Range: -2.0718

Max Act: 1.6373. Min Act: -0.0000

Data Index: 1434358 (Python Code)

Max Activating Token Index: 809

Text #6

Max Range: 2.0718. Min Range: -2.0718

Max Act: 1.8031. Min Act: -0.0000

Data Index: 1502484 (Python Code)

Max Activating Token Index: 899

Text #7

Max Range: 2.0718. Min Range: -2.0718

Max Act: 1.8163. Min Act: -0.0000

Data Index: 1538174 (Python Code)

Max Activating Token Index: 940

Text #8

Max Range: 2.0718. Min Range: -2.0718

Max Act: 1.6682. Min Act: -0.0000

Data Index: 1654175 (Python Code)

Max Activating Token Index: 583

Text #9

Max Range: 2.0718. Min Range: -2.0718

Max Act: 1.7968. Min Act: -0.0000

Data Index: 1485600 (Python Code)

Max Activating Token Index: 658

Text #10

Max Range: 2.0718. Min Range: -2.0718

Max Act: 1.7949. Min Act: -0.0000

Data Index: 1447497 (Python Code)

Max Activating Token Index: 134

Text #11

Max Range: 2.0718. Min Range: -2.0718

Max Act: 1.6266. Min Act: -0.0000

Data Index: 1621149 (Python Code)

Max Activating Token Index: 693

Text #12

Max Range: 2.0718. Min Range: -2.0718

Max Act: 1.6134. Min Act: -0.0000

Data Index: 1367133 (Python Code)

Max Activating Token Index: 260

Text #13

Max Range: 2.0718. Min Range: -2.0718

Max Act: 1.5515. Min Act: -0.0000

Data Index: 1446770 (Python Code)

Max Activating Token Index: 978

Text #14

Max Range: 2.0718. Min Range: -2.0718

Max Act: 1.6091. Min Act: -0.0000

Data Index: 1522215 (Python Code)

Max Activating Token Index: 180

Text #15

Max Range: 2.0718. Min Range: -2.0718

Max Act: 1.6120. Min Act: -0.0000

Data Index: 1624970 (Python Code)

Max Activating Token Index: 49

Text #16

Max Range: 2.0718. Min Range: -2.0718

Max Act: 1.6107. Min Act: -0.0000

Data Index: 1531487 (Python Code)

Max Activating Token Index: 505

Text #17

Max Range: 2.0718. Min Range: -2.0718

Max Act: 1.7591. Min Act: -0.0000

Data Index: 1567419 (Python Code)

Max Activating Token Index: 806

Text #18

Max Range: 2.0718. Min Range: -2.0718

Max Act: 1.6055. Min Act: -0.0000

Data Index: 1368013 (Python Code)

Max Activating Token Index: 850

Text #19

Max Range: 2.0718. Min Range: -2.0718

Max Act: 1.6041. Min Act: -0.0000

Data Index: 1553823 (Python Code)

Max Activating Token Index: 418