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

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

Neuron 2810 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.7975. Min Act: 0.0000

Data Index: 680703 (C4 (Web Text))

Max Activating Token Index: 810

Text #1

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.4149. Min Act: -0.0000

Data Index: 1086803 (C4 (Web Text))

Max Activating Token Index: 383

Text #2

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.4277. Min Act: -0.0000

Data Index: 817271 (C4 (Web Text))

Max Activating Token Index: 425

Text #3

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.4914. Min Act: 0.0000

Data Index: 99091 (C4 (Web Text))

Max Activating Token Index: 261

Text #4

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.3882. Min Act: -0.0000

Data Index: 687404 (C4 (Web Text))

Max Activating Token Index: 954

Text #5

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.4056. Min Act: -0.0000

Data Index: 301550 (C4 (Web Text))

Max Activating Token Index: 376

Text #6

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.2705. Min Act: -0.0000

Data Index: 1271522 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.4029. Min Act: -0.0000

Data Index: 626211 (C4 (Web Text))

Max Activating Token Index: 519

Text #8

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.3239. Min Act: -0.0000

Data Index: 127888 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.2288. Min Act: -0.0000

Data Index: 93813 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.2238. Min Act: -0.0000

Data Index: 164884 (C4 (Web Text))

Max Activating Token Index: 556

Text #11

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.1952. Min Act: -0.0000

Data Index: 198613 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.1861. Min Act: -0.0000

Data Index: 637041 (C4 (Web Text))

Max Activating Token Index: 958

Text #13

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.1007. Min Act: -0.0000

Data Index: 325779 (C4 (Web Text))

Max Activating Token Index: 660

Text #14

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.1603. Min Act: -0.0000

Data Index: 1189937 (C4 (Web Text))

Max Activating Token Index: 599

Text #15

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.1589. Min Act: 0.0000

Data Index: 153404 (C4 (Web Text))

Max Activating Token Index: 766

Text #16

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.0783. Min Act: -0.0000

Data Index: 585588 (C4 (Web Text))

Max Activating Token Index: 657

Text #17

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.1386. Min Act: -0.0000

Data Index: 709998 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.1346. Min Act: -0.0000

Data Index: 716390 (C4 (Web Text))

Max Activating Token Index: 534

Text #19

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.0636. Min Act: -0.0000

Data Index: 347176 (C4 (Web Text))

Max Activating Token Index: 853