Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1929 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.2847. Min Range: -2.2847

Max Act: 2.2847. Min Act: -0.0000

Data Index: 1544543 (Python Code)

Max Activating Token Index: 412

Text #1

Max Range: 2.2847. Min Range: -2.2847

Max Act: 2.2002. Min Act: -0.0000

Data Index: 1565021 (Python Code)

Max Activating Token Index: 697

Text #2

Max Range: 2.2847. Min Range: -2.2847

Max Act: 2.1439. Min Act: -0.0000

Data Index: 1504267 (Python Code)

Max Activating Token Index: 199

Text #3

Max Range: 2.2847. Min Range: -2.2847

Max Act: 2.0154. Min Act: -0.0000

Data Index: 1622946 (Python Code)

Max Activating Token Index: 54

Text #4

Max Range: 2.2847. Min Range: -2.2847

Max Act: 1.9409. Min Act: -0.0000

Data Index: 1502992 (Python Code)

Max Activating Token Index: 278

Text #5

Max Range: 2.2847. Min Range: -2.2847

Max Act: 1.8880. Min Act: -0.0000

Data Index: 1504001 (Python Code)

Max Activating Token Index: 209

Text #6

Max Range: 2.2847. Min Range: -2.2847

Max Act: 1.8783. Min Act: -0.0000

Data Index: 178332 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 2.2847. Min Range: -2.2847

Max Act: 1.9765. Min Act: -0.0000

Data Index: 1641838 (Python Code)

Max Activating Token Index: 105

Text #8

Max Range: 2.2847. Min Range: -2.2847

Max Act: 1.7628. Min Act: -0.0000

Data Index: 1561976 (Python Code)

Max Activating Token Index: 750

Text #9

Max Range: 2.2847. Min Range: -2.2847

Max Act: 1.8524. Min Act: -0.0000

Data Index: 1409937 (Python Code)

Max Activating Token Index: 63

Text #10

Max Range: 2.2847. Min Range: -2.2847

Max Act: 1.8245. Min Act: -0.0000

Data Index: 1611320 (Python Code)

Max Activating Token Index: 189

Text #11

Max Range: 2.2847. Min Range: -2.2847

Max Act: 1.8245. Min Act: -0.0000

Data Index: 1474160 (Python Code)

Max Activating Token Index: 410

Text #12

Max Range: 2.2847. Min Range: -2.2847

Max Act: 1.6973. Min Act: -0.0000

Data Index: 1434300 (Python Code)

Max Activating Token Index: 130

Text #13

Max Range: 2.2847. Min Range: -2.2847

Max Act: 1.7932. Min Act: -0.0000

Data Index: 1376747 (Python Code)

Max Activating Token Index: 640

Text #14

Max Range: 2.2847. Min Range: -2.2847

Max Act: 1.7897. Min Act: -0.0000

Data Index: 1449350 (Python Code)

Max Activating Token Index: 78

Text #15

Max Range: 2.2847. Min Range: -2.2847

Max Act: 1.8856. Min Act: -0.0000

Data Index: 1419794 (Python Code)

Max Activating Token Index: 894

Text #16

Max Range: 2.2847. Min Range: -2.2847

Max Act: 1.7588. Min Act: -0.0000

Data Index: 1488070 (Python Code)

Max Activating Token Index: 711

Text #17

Max Range: 2.2847. Min Range: -2.2847

Max Act: 1.7524. Min Act: -0.0000

Data Index: 1450318 (Python Code)

Max Activating Token Index: 311

Text #18

Max Range: 2.2847. Min Range: -2.2847

Max Act: 1.7475. Min Act: -0.0000

Data Index: 1583737 (Python Code)

Max Activating Token Index: 418

Text #19

Max Range: 2.2847. Min Range: -2.2847

Max Act: 1.7458. Min Act: -0.0000

Data Index: 1376558 (Python Code)

Max Activating Token Index: 730