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

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

Neuron 89 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7867. Min Range: -1.7867

Max Act: 1.7867. Min Act: -0.0000

Data Index: 897357 (C4 (Web Text))

Max Activating Token Index: 914

Text #1

Max Range: 1.7867. Min Range: -1.7867

Max Act: 1.5640. Min Act: -0.0000

Data Index: 1445077 (Python Code)

Max Activating Token Index: 451

Text #2

Max Range: 1.7867. Min Range: -1.7867

Max Act: 1.3695. Min Act: -0.0000

Data Index: 1336400 (C4 (Web Text))

Max Activating Token Index: 909

Text #3

Max Range: 1.7867. Min Range: -1.7867

Max Act: 1.4022. Min Act: -0.0000

Data Index: 1348434 (C4 (Web Text))

Max Activating Token Index: 1005

Text #4

Max Range: 1.7867. Min Range: -1.7867

Max Act: 1.3982. Min Act: -0.0000

Data Index: 1620190 (Python Code)

Max Activating Token Index: 351

Text #5

Max Range: 1.7867. Min Range: -1.7867

Max Act: 1.3871. Min Act: -0.0000

Data Index: 606620 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 1.7867. Min Range: -1.7867

Max Act: 1.6346. Min Act: -0.0000

Data Index: 484689 (C4 (Web Text))

Max Activating Token Index: 271

Text #7

Max Range: 1.7867. Min Range: -1.7867

Max Act: 1.3358. Min Act: 0.0000

Data Index: 1629925 (Python Code)

Max Activating Token Index: 882

Text #8

Max Range: 1.7867. Min Range: -1.7867

Max Act: 1.4286. Min Act: -0.0000

Data Index: 1548516 (Python Code)

Max Activating Token Index: 407

Text #9

Max Range: 1.7867. Min Range: -1.7867

Max Act: 1.2520. Min Act: -0.0000

Data Index: 925677 (C4 (Web Text))

Max Activating Token Index: 888

Text #10

Max Range: 1.7867. Min Range: -1.7867

Max Act: 1.4028. Min Act: -0.0000

Data Index: 253106 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 1.7867. Min Range: -1.7867

Max Act: 1.2489. Min Act: -0.0000

Data Index: 135343 (C4 (Web Text))

Max Activating Token Index: 320

Text #12

Max Range: 1.7867. Min Range: -1.7867

Max Act: 1.2346. Min Act: -0.0000

Data Index: 1532186 (Python Code)

Max Activating Token Index: 811

Text #13

Max Range: 1.7867. Min Range: -1.7867

Max Act: 1.3212. Min Act: -0.0000

Data Index: 975092 (C4 (Web Text))

Max Activating Token Index: 320

Text #14

Max Range: 1.7867. Min Range: -1.7867

Max Act: 1.2532. Min Act: -0.0000

Data Index: 1629526 (Python Code)

Max Activating Token Index: 394

Text #15

Max Range: 1.7867. Min Range: -1.7867

Max Act: 1.1646. Min Act: -0.0000

Data Index: 1368048 (Python Code)

Max Activating Token Index: 660

Text #16

Max Range: 1.7867. Min Range: -1.7867

Max Act: 1.3078. Min Act: -0.0000

Data Index: 1383371 (Python Code)

Max Activating Token Index: 61

Text #17

Max Range: 1.7867. Min Range: -1.7867

Max Act: 1.2820. Min Act: -0.0000

Data Index: 1655823 (Python Code)

Max Activating Token Index: 583

Text #18

Max Range: 1.7867. Min Range: -1.7867

Max Act: 1.2203. Min Act: -0.0000

Data Index: 1419318 (Python Code)

Max Activating Token Index: 957

Text #19

Max Range: 1.7867. Min Range: -1.7867

Max Act: 1.1770. Min Act: -0.0000

Data Index: 779638 (C4 (Web Text))

Max Activating Token Index: 1012