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

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

Neuron 4860 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7053. Min Range: -2.7053

Max Act: 2.7053. Min Act: -0.0000

Data Index: 1564891 (Python Code)

Max Activating Token Index: 827

Text #1

Max Range: 2.7053. Min Range: -2.7053

Max Act: 2.4654. Min Act: -0.0000

Data Index: 1489986 (Python Code)

Max Activating Token Index: 731

Text #2

Max Range: 2.7053. Min Range: -2.7053

Max Act: 2.0910. Min Act: -0.0000

Data Index: 742137 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 2.7053. Min Range: -2.7053

Max Act: 1.8684. Min Act: -0.0000

Data Index: 937465 (C4 (Web Text))

Max Activating Token Index: 346

Text #4

Max Range: 2.7053. Min Range: -2.7053

Max Act: 2.3265. Min Act: -0.0000

Data Index: 1482822 (Python Code)

Max Activating Token Index: 216

Text #5

Max Range: 2.7053. Min Range: -2.7053

Max Act: 1.9784. Min Act: -0.0000

Data Index: 1656200 (Python Code)

Max Activating Token Index: 101

Text #6

Max Range: 2.7053. Min Range: -2.7053

Max Act: 1.8297. Min Act: -0.0000

Data Index: 1468021 (Python Code)

Max Activating Token Index: 865

Text #7

Max Range: 2.7053. Min Range: -2.7053

Max Act: 2.0411. Min Act: -0.0000

Data Index: 642379 (C4 (Web Text))

Max Activating Token Index: 143

Text #8

Max Range: 2.7053. Min Range: -2.7053

Max Act: 2.1076. Min Act: -0.0000

Data Index: 388197 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 2.7053. Min Range: -2.7053

Max Act: 1.9440. Min Act: -0.0000

Data Index: 1462883 (Python Code)

Max Activating Token Index: 95

Text #10

Max Range: 2.7053. Min Range: -2.7053

Max Act: 1.9169. Min Act: -0.0000

Data Index: 1086662 (C4 (Web Text))

Max Activating Token Index: 169

Text #11

Max Range: 2.7053. Min Range: -2.7053

Max Act: 1.9303. Min Act: -0.0000

Data Index: 1453209 (Python Code)

Max Activating Token Index: 996

Text #12

Max Range: 2.7053. Min Range: -2.7053

Max Act: 1.7984. Min Act: -0.0000

Data Index: 596113 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 2.7053. Min Range: -2.7053

Max Act: 1.7959. Min Act: -0.0000

Data Index: 181016 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 2.7053. Min Range: -2.7053

Max Act: 1.7001. Min Act: -0.0000

Data Index: 225466 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 2.7053. Min Range: -2.7053

Max Act: 1.8325. Min Act: -0.0000

Data Index: 1542361 (Python Code)

Max Activating Token Index: 433

Text #16

Max Range: 2.7053. Min Range: -2.7053

Max Act: 1.8493. Min Act: -0.0000

Data Index: 632617 (C4 (Web Text))

Max Activating Token Index: 869

Text #17

Max Range: 2.7053. Min Range: -2.7053

Max Act: 1.8360. Min Act: -0.0000

Data Index: 936494 (C4 (Web Text))

Max Activating Token Index: 660

Text #18

Max Range: 2.7053. Min Range: -2.7053

Max Act: 1.7622. Min Act: -0.0000

Data Index: 42390 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 2.7053. Min Range: -2.7053

Max Act: 1.9515. Min Act: -0.0000

Data Index: 1534199 (Python Code)

Max Activating Token Index: 401