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

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

Neuron 4938 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.2321. Min Act: -0.0000

Data Index: 407442 (C4 (Web Text))

Max Activating Token Index: 472

Text #1

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.2454. Min Act: -0.0000

Data Index: 276258 (C4 (Web Text))

Max Activating Token Index: 925

Text #2

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.2143. Min Act: -0.0000

Data Index: 197830 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.2081. Min Act: -0.0000

Data Index: 398216 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.1938. Min Act: -0.0000

Data Index: 108084 (C4 (Web Text))

Max Activating Token Index: 812

Text #5

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.1872. Min Act: -0.0000

Data Index: 885786 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.2063. Min Act: -0.0000

Data Index: 1110273 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.1757. Min Act: -0.0000

Data Index: 249688 (C4 (Web Text))

Max Activating Token Index: 418

Text #8

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.1715. Min Act: 0.0000

Data Index: 218427 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.1689. Min Act: -0.0000

Data Index: 55340 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.1808. Min Act: -0.0000

Data Index: 258543 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.1644. Min Act: 0.0000

Data Index: 1330838 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.1669. Min Act: -0.0000

Data Index: 526314 (C4 (Web Text))

Max Activating Token Index: 707

Text #13

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.1589. Min Act: -0.0000

Data Index: 1126038 (C4 (Web Text))

Max Activating Token Index: 454

Text #14

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.1569. Min Act: -0.0000

Data Index: 469252 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.1517. Min Act: -0.0000

Data Index: 626925 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.1476. Min Act: -0.0000

Data Index: 730898 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.1495. Min Act: -0.0000

Data Index: 878452 (C4 (Web Text))

Max Activating Token Index: 611

Text #18

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.1453. Min Act: -0.0000

Data Index: 1075580 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.1486. Min Act: -0.0000

Data Index: 930405 (C4 (Web Text))

Max Activating Token Index: 30