Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2359 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4655. Min Range: -1.4655

Max Act: 1.4655. Min Act: -0.0000

Data Index: 1394853 (Python Code)

Max Activating Token Index: 620

Text #1

Max Range: 1.4655. Min Range: -1.4655

Max Act: 1.4521. Min Act: -0.0000

Data Index: 1535473 (Python Code)

Max Activating Token Index: 803

Text #2

Max Range: 1.4655. Min Range: -1.4655

Max Act: 1.3432. Min Act: -0.0000

Data Index: 1558299 (Python Code)

Max Activating Token Index: 325

Text #3

Max Range: 1.4655. Min Range: -1.4655

Max Act: 1.1899. Min Act: -0.0000

Data Index: 1460101 (Python Code)

Max Activating Token Index: 749

Text #4

Max Range: 1.4655. Min Range: -1.4655

Max Act: 1.2448. Min Act: -0.0000

Data Index: 1616799 (Python Code)

Max Activating Token Index: 430

Text #5

Max Range: 1.4655. Min Range: -1.4655

Max Act: 1.1652. Min Act: -0.0000

Data Index: 1651121 (Python Code)

Max Activating Token Index: 36

Text #6

Max Range: 1.4655. Min Range: -1.4655

Max Act: 1.1360. Min Act: -0.0000

Data Index: 1611635 (Python Code)

Max Activating Token Index: 114

Text #7

Max Range: 1.4655. Min Range: -1.4655

Max Act: 1.0748. Min Act: -0.0000

Data Index: 1633675 (Python Code)

Max Activating Token Index: 1018

Text #8

Max Range: 1.4655. Min Range: -1.4655

Max Act: 1.1135. Min Act: -0.0000

Data Index: 1396463 (Python Code)

Max Activating Token Index: 273

Text #9

Max Range: 1.4655. Min Range: -1.4655

Max Act: 1.1197. Min Act: -0.0000

Data Index: 1508577 (Python Code)

Max Activating Token Index: 186

Text #10

Max Range: 1.4655. Min Range: -1.4655

Max Act: 1.0823. Min Act: -0.0000

Data Index: 1608905 (Python Code)

Max Activating Token Index: 94

Text #11

Max Range: 1.4655. Min Range: -1.4655

Max Act: 1.0471. Min Act: -0.0000

Data Index: 1519417 (Python Code)

Max Activating Token Index: 754

Text #12

Max Range: 1.4655. Min Range: -1.4655

Max Act: 1.1218. Min Act: -0.0000

Data Index: 1574246 (Python Code)

Max Activating Token Index: 441

Text #13

Max Range: 1.4655. Min Range: -1.4655

Max Act: 1.0413. Min Act: -0.0000

Data Index: 1463471 (Python Code)

Max Activating Token Index: 654

Text #14

Max Range: 1.4655. Min Range: -1.4655

Max Act: 1.0478. Min Act: -0.0000

Data Index: 1621255 (Python Code)

Max Activating Token Index: 568

Text #15

Max Range: 1.4655. Min Range: -1.4655

Max Act: 1.1349. Min Act: -0.0000

Data Index: 1652822 (Python Code)

Max Activating Token Index: 327

Text #16

Max Range: 1.4655. Min Range: -1.4655

Max Act: 1.0251. Min Act: -0.0000

Data Index: 1639122 (Python Code)

Max Activating Token Index: 116

Text #17

Max Range: 1.4655. Min Range: -1.4655

Max Act: 0.9734. Min Act: -0.0000

Data Index: 1594820 (Python Code)

Max Activating Token Index: 226

Text #18

Max Range: 1.4655. Min Range: -1.4655

Max Act: 1.0642. Min Act: -0.0000

Data Index: 1401157 (Python Code)

Max Activating Token Index: 87

Text #19

Max Range: 1.4655. Min Range: -1.4655

Max Act: 1.0155. Min Act: -0.0000

Data Index: 1630645 (Python Code)

Max Activating Token Index: 558