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

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

Neuron 4750 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: 3.0310. Min Range: -3.0310

Max Act: 2.8968. Min Act: -0.0000

Data Index: 1502691 (Python Code)

Max Activating Token Index: 181

Text #1

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.9760. Min Act: -0.0000

Data Index: 1478282 (Python Code)

Max Activating Token Index: 273

Text #2

Max Range: 3.0310. Min Range: -3.0310

Max Act: 3.0310. Min Act: -0.0000

Data Index: 1548299 (Python Code)

Max Activating Token Index: 587

Text #3

Max Range: 3.0310. Min Range: -3.0310

Max Act: 3.0110. Min Act: -0.0000

Data Index: 1417544 (Python Code)

Max Activating Token Index: 446

Text #4

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.8566. Min Act: -0.0000

Data Index: 1553442 (Python Code)

Max Activating Token Index: 289

Text #5

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.8441. Min Act: -0.0000

Data Index: 1491200 (Python Code)

Max Activating Token Index: 331

Text #6

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.8028. Min Act: -0.0000

Data Index: 1598703 (Python Code)

Max Activating Token Index: 433

Text #7

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.6103. Min Act: -0.0000

Data Index: 1431975 (Python Code)

Max Activating Token Index: 347

Text #8

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.7004. Min Act: -0.0000

Data Index: 1632822 (Python Code)

Max Activating Token Index: 682

Text #9

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.7989. Min Act: -0.0000

Data Index: 1542699 (Python Code)

Max Activating Token Index: 784

Text #10

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.6917. Min Act: -0.0000

Data Index: 1581672 (Python Code)

Max Activating Token Index: 278

Text #11

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.8086. Min Act: -0.0000

Data Index: 1603449 (Python Code)

Max Activating Token Index: 412

Text #12

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.5309. Min Act: -0.0000

Data Index: 1644361 (Python Code)

Max Activating Token Index: 816

Text #13

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.6832. Min Act: -0.0000

Data Index: 1442742 (Python Code)

Max Activating Token Index: 535

Text #14

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.6929. Min Act: -0.0000

Data Index: 1512680 (Python Code)

Max Activating Token Index: 947

Text #15

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.6933. Min Act: -0.0000

Data Index: 1456360 (Python Code)

Max Activating Token Index: 961

Text #16

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.5945. Min Act: -0.0000

Data Index: 1579710 (Python Code)

Max Activating Token Index: 173

Text #17

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.5906. Min Act: -0.0000

Data Index: 1449396 (Python Code)

Max Activating Token Index: 541

Text #18

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.6021. Min Act: -0.0000

Data Index: 1387467 (Python Code)

Max Activating Token Index: 490

Text #19

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.7268. Min Act: -0.0000

Data Index: 1492885 (Python Code)

Max Activating Token Index: 483