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

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

Neuron 5165 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5922. Min Range: -2.5922

Max Act: 2.5922. Min Act: -0.0000

Data Index: 381983 (C4 (Web Text))

Max Activating Token Index: 743

Text #1

Max Range: 2.5922. Min Range: -2.5922

Max Act: 2.1429. Min Act: -0.0000

Data Index: 145042 (C4 (Web Text))

Max Activating Token Index: 752

Text #2

Max Range: 2.5922. Min Range: -2.5922

Max Act: 2.2184. Min Act: -0.0000

Data Index: 1155127 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 2.5922. Min Range: -2.5922

Max Act: 2.2233. Min Act: -0.0000

Data Index: 1264899 (C4 (Web Text))

Max Activating Token Index: 279

Text #4

Max Range: 2.5922. Min Range: -2.5922

Max Act: 2.2012. Min Act: -0.0000

Data Index: 834160 (C4 (Web Text))

Max Activating Token Index: 428

Text #5

Max Range: 2.5922. Min Range: -2.5922

Max Act: 2.3081. Min Act: -0.0000

Data Index: 534749 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 2.5922. Min Range: -2.5922

Max Act: 2.1850. Min Act: -0.0000

Data Index: 314055 (C4 (Web Text))

Max Activating Token Index: 346

Text #7

Max Range: 2.5922. Min Range: -2.5922

Max Act: 2.1883. Min Act: -0.0000

Data Index: 1032614 (C4 (Web Text))

Max Activating Token Index: 909

Text #8

Max Range: 2.5922. Min Range: -2.5922

Max Act: 2.1291. Min Act: -0.0000

Data Index: 473890 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 2.5922. Min Range: -2.5922

Max Act: 2.1154. Min Act: -0.0000

Data Index: 387928 (C4 (Web Text))

Max Activating Token Index: 950

Text #10

Max Range: 2.5922. Min Range: -2.5922

Max Act: 2.0935. Min Act: -0.0000

Data Index: 531959 (C4 (Web Text))

Max Activating Token Index: 558

Text #11

Max Range: 2.5922. Min Range: -2.5922

Max Act: 2.0749. Min Act: -0.0000

Data Index: 793036 (C4 (Web Text))

Max Activating Token Index: 306

Text #12

Max Range: 2.5922. Min Range: -2.5922

Max Act: 2.1793. Min Act: -0.0000

Data Index: 100879 (C4 (Web Text))

Max Activating Token Index: 692

Text #13

Max Range: 2.5922. Min Range: -2.5922

Max Act: 2.0550. Min Act: -0.0000

Data Index: 1064533 (C4 (Web Text))

Max Activating Token Index: 407

Text #14

Max Range: 2.5922. Min Range: -2.5922

Max Act: 1.9285. Min Act: -0.0000

Data Index: 1246257 (C4 (Web Text))

Max Activating Token Index: 945

Text #15

Max Range: 2.5922. Min Range: -2.5922

Max Act: 2.1622. Min Act: -0.0000

Data Index: 276862 (C4 (Web Text))

Max Activating Token Index: 691

Text #16

Max Range: 2.5922. Min Range: -2.5922

Max Act: 1.9193. Min Act: -0.0000

Data Index: 629958 (C4 (Web Text))

Max Activating Token Index: 14

Text #17

Max Range: 2.5922. Min Range: -2.5922

Max Act: 2.0278. Min Act: -0.0000

Data Index: 1125543 (C4 (Web Text))

Max Activating Token Index: 723

Text #18

Max Range: 2.5922. Min Range: -2.5922

Max Act: 1.9255. Min Act: -0.0000

Data Index: 1212574 (C4 (Web Text))

Max Activating Token Index: 926

Text #19

Max Range: 2.5922. Min Range: -2.5922

Max Act: 1.9447. Min Act: -0.0000

Data Index: 452065 (C4 (Web Text))

Max Activating Token Index: 768