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

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

Neuron 2541 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2000. Min Range: -4.2000

Max Act: 3.6961. Min Act: -0.0000

Data Index: 1382463 (Python Code)

Max Activating Token Index: 818

Text #1

Max Range: 4.2000. Min Range: -4.2000

Max Act: 4.2000. Min Act: -0.0000

Data Index: 1517196 (Python Code)

Max Activating Token Index: 101

Text #2

Max Range: 4.2000. Min Range: -4.2000

Max Act: 3.6398. Min Act: -0.0000

Data Index: 1438455 (Python Code)

Max Activating Token Index: 805

Text #3

Max Range: 4.2000. Min Range: -4.2000

Max Act: 3.6826. Min Act: -0.0000

Data Index: 1566258 (Python Code)

Max Activating Token Index: 288

Text #4

Max Range: 4.2000. Min Range: -4.2000

Max Act: 3.5181. Min Act: -0.0000

Data Index: 1396762 (Python Code)

Max Activating Token Index: 418

Text #5

Max Range: 4.2000. Min Range: -4.2000

Max Act: 3.4040. Min Act: -0.0000

Data Index: 1580125 (Python Code)

Max Activating Token Index: 473

Text #6

Max Range: 4.2000. Min Range: -4.2000

Max Act: 3.2653. Min Act: -0.0000

Data Index: 1635980 (Python Code)

Max Activating Token Index: 326

Text #7

Max Range: 4.2000. Min Range: -4.2000

Max Act: 3.1424. Min Act: -0.0000

Data Index: 1565407 (Python Code)

Max Activating Token Index: 572

Text #8

Max Range: 4.2000. Min Range: -4.2000

Max Act: 3.0977. Min Act: -0.0000

Data Index: 1560832 (Python Code)

Max Activating Token Index: 509

Text #9

Max Range: 4.2000. Min Range: -4.2000

Max Act: 3.1156. Min Act: -0.0000

Data Index: 1472714 (Python Code)

Max Activating Token Index: 427

Text #10

Max Range: 4.2000. Min Range: -4.2000

Max Act: 3.0734. Min Act: -0.0000

Data Index: 1556103 (Python Code)

Max Activating Token Index: 889

Text #11

Max Range: 4.2000. Min Range: -4.2000

Max Act: 3.0369. Min Act: -0.0000

Data Index: 1582954 (Python Code)

Max Activating Token Index: 796

Text #12

Max Range: 4.2000. Min Range: -4.2000

Max Act: 2.8365. Min Act: -0.0000

Data Index: 1505133 (Python Code)

Max Activating Token Index: 179

Text #13

Max Range: 4.2000. Min Range: -4.2000

Max Act: 2.9477. Min Act: -0.0000

Data Index: 1641989 (Python Code)

Max Activating Token Index: 129

Text #14

Max Range: 4.2000. Min Range: -4.2000

Max Act: 2.9451. Min Act: -0.0000

Data Index: 1442532 (Python Code)

Max Activating Token Index: 356

Text #15

Max Range: 4.2000. Min Range: -4.2000

Max Act: 2.9440. Min Act: -0.0000

Data Index: 1526126 (Python Code)

Max Activating Token Index: 336

Text #16

Max Range: 4.2000. Min Range: -4.2000

Max Act: 2.9380. Min Act: -0.0000

Data Index: 1473331 (Python Code)

Max Activating Token Index: 144

Text #17

Max Range: 4.2000. Min Range: -4.2000

Max Act: 2.9252. Min Act: -0.0000

Data Index: 1651735 (Python Code)

Max Activating Token Index: 505

Text #18

Max Range: 4.2000. Min Range: -4.2000

Max Act: 2.7595. Min Act: -0.0000

Data Index: 1396272 (Python Code)

Max Activating Token Index: 757

Text #19

Max Range: 4.2000. Min Range: -4.2000

Max Act: 2.8525. Min Act: -0.0000

Data Index: 1654670 (Python Code)

Max Activating Token Index: 52