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

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

Neuron 1041 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: 2.7812. Min Range: -2.7812

Max Act: 2.6770. Min Act: -0.0000

Data Index: 310683 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 2.7812. Min Range: -2.7812

Max Act: 2.6873. Min Act: -0.0000

Data Index: 906500 (C4 (Web Text))

Max Activating Token Index: 629

Text #2

Max Range: 2.7812. Min Range: -2.7812

Max Act: 2.6751. Min Act: -0.0000

Data Index: 1029499 (C4 (Web Text))

Max Activating Token Index: 654

Text #3

Max Range: 2.7812. Min Range: -2.7812

Max Act: 2.7812. Min Act: -0.0000

Data Index: 631417 (C4 (Web Text))

Max Activating Token Index: 676

Text #4

Max Range: 2.7812. Min Range: -2.7812

Max Act: 2.4502. Min Act: -0.0000

Data Index: 647079 (C4 (Web Text))

Max Activating Token Index: 601

Text #5

Max Range: 2.7812. Min Range: -2.7812

Max Act: 2.5715. Min Act: -0.0000

Data Index: 278192 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 2.7812. Min Range: -2.7812

Max Act: 2.5294. Min Act: -0.0000

Data Index: 684930 (C4 (Web Text))

Max Activating Token Index: 541

Text #7

Max Range: 2.7812. Min Range: -2.7812

Max Act: 2.4975. Min Act: -0.0000

Data Index: 1206267 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 2.7812. Min Range: -2.7812

Max Act: 2.6565. Min Act: -0.0000

Data Index: 425743 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 2.7812. Min Range: -2.7812

Max Act: 2.2802. Min Act: -0.0000

Data Index: 937987 (C4 (Web Text))

Max Activating Token Index: 298

Text #10

Max Range: 2.7812. Min Range: -2.7812

Max Act: 2.4119. Min Act: -0.0000

Data Index: 1282647 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 2.7812. Min Range: -2.7812

Max Act: 2.3944. Min Act: -0.0000

Data Index: 262910 (C4 (Web Text))

Max Activating Token Index: 566

Text #12

Max Range: 2.7812. Min Range: -2.7812

Max Act: 2.3435. Min Act: -0.0000

Data Index: 695530 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 2.7812. Min Range: -2.7812

Max Act: 2.3326. Min Act: -0.0000

Data Index: 310226 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 2.7812. Min Range: -2.7812

Max Act: 2.3460. Min Act: -0.0000

Data Index: 494583 (C4 (Web Text))

Max Activating Token Index: 707

Text #15

Max Range: 2.7812. Min Range: -2.7812

Max Act: 2.3351. Min Act: -0.0000

Data Index: 982767 (C4 (Web Text))

Max Activating Token Index: 1001

Text #16

Max Range: 2.7812. Min Range: -2.7812

Max Act: 2.3196. Min Act: -0.0000

Data Index: 1099041 (C4 (Web Text))

Max Activating Token Index: 809

Text #17

Max Range: 2.7812. Min Range: -2.7812

Max Act: 2.3188. Min Act: -0.0000

Data Index: 1290771 (C4 (Web Text))

Max Activating Token Index: 150

Text #18

Max Range: 2.7812. Min Range: -2.7812

Max Act: 2.2101. Min Act: -0.0000

Data Index: 315617 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 2.7812. Min Range: -2.7812

Max Act: 2.3127. Min Act: -0.0000

Data Index: 477666 (C4 (Web Text))

Max Activating Token Index: 700