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

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

Neuron 1519 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: 2.3360. Min Range: -2.3360

Max Act: 2.3360. Min Act: -0.0000

Data Index: 1391481 (Python Code)

Max Activating Token Index: 399

Text #1

Max Range: 2.3360. Min Range: -2.3360

Max Act: 2.1167. Min Act: -0.0000

Data Index: 1623251 (Python Code)

Max Activating Token Index: 294

Text #2

Max Range: 2.3360. Min Range: -2.3360

Max Act: 2.1166. Min Act: -0.0000

Data Index: 1530543 (Python Code)

Max Activating Token Index: 993

Text #3

Max Range: 2.3360. Min Range: -2.3360

Max Act: 2.2730. Min Act: -0.0000

Data Index: 1408687 (Python Code)

Max Activating Token Index: 332

Text #4

Max Range: 2.3360. Min Range: -2.3360

Max Act: 1.9631. Min Act: -0.0000

Data Index: 1613617 (Python Code)

Max Activating Token Index: 244

Text #5

Max Range: 2.3360. Min Range: -2.3360

Max Act: 2.0611. Min Act: -0.0000

Data Index: 1455903 (Python Code)

Max Activating Token Index: 620

Text #6

Max Range: 2.3360. Min Range: -2.3360

Max Act: 1.9424. Min Act: -0.0000

Data Index: 1497631 (Python Code)

Max Activating Token Index: 401

Text #7

Max Range: 2.3360. Min Range: -2.3360

Max Act: 2.0409. Min Act: -0.0000

Data Index: 1651729 (Python Code)

Max Activating Token Index: 498

Text #8

Max Range: 2.3360. Min Range: -2.3360

Max Act: 1.9448. Min Act: -0.0000

Data Index: 1414888 (Python Code)

Max Activating Token Index: 426

Text #9

Max Range: 2.3360. Min Range: -2.3360

Max Act: 1.9871. Min Act: -0.0000

Data Index: 1465699 (Python Code)

Max Activating Token Index: 440

Text #10

Max Range: 2.3360. Min Range: -2.3360

Max Act: 1.9658. Min Act: -0.0000

Data Index: 1571217 (Python Code)

Max Activating Token Index: 417

Text #11

Max Range: 2.3360. Min Range: -2.3360

Max Act: 2.1856. Min Act: -0.0000

Data Index: 1449469 (Python Code)

Max Activating Token Index: 931

Text #12

Max Range: 2.3360. Min Range: -2.3360

Max Act: 2.0090. Min Act: -0.0000

Data Index: 1606613 (Python Code)

Max Activating Token Index: 511

Text #13

Max Range: 2.3360. Min Range: -2.3360

Max Act: 1.9419. Min Act: -0.0000

Data Index: 1635731 (Python Code)

Max Activating Token Index: 663

Text #14

Max Range: 2.3360. Min Range: -2.3360

Max Act: 1.8810. Min Act: -0.0000

Data Index: 1451660 (Python Code)

Max Activating Token Index: 795

Text #15

Max Range: 2.3360. Min Range: -2.3360

Max Act: 1.9276. Min Act: -0.0000

Data Index: 1524677 (Python Code)

Max Activating Token Index: 437

Text #16

Max Range: 2.3360. Min Range: -2.3360

Max Act: 1.9771. Min Act: -0.0000

Data Index: 1487604 (Python Code)

Max Activating Token Index: 360

Text #17

Max Range: 2.3360. Min Range: -2.3360

Max Act: 1.9300. Min Act: -0.0000

Data Index: 1445270 (Python Code)

Max Activating Token Index: 397

Text #18

Max Range: 2.3360. Min Range: -2.3360

Max Act: 1.9347. Min Act: -0.0000

Data Index: 1514863 (Python Code)

Max Activating Token Index: 449

Text #19

Max Range: 2.3360. Min Range: -2.3360

Max Act: 2.0222. Min Act: -0.0000

Data Index: 1498082 (Python Code)

Max Activating Token Index: 417