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

Dataset: The Pile

Neuron 416 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1338. Min Range: -1.1338

Max Act: 1.1338. Min Act: -0.0000

Data Index: 1360608 (The Pile)

Max Activating Token Index: 855

Text #1

Max Range: 1.1338. Min Range: -1.1338

Max Act: 1.0368. Min Act: -0.0000

Data Index: 873633 (The Pile)

Max Activating Token Index: 321

Text #2

Max Range: 1.1338. Min Range: -1.1338

Max Act: 0.9909. Min Act: -0.0000

Data Index: 1143802 (The Pile)

Max Activating Token Index: 692

Text #3

Max Range: 1.1338. Min Range: -1.1338

Max Act: 0.9977. Min Act: -0.0000

Data Index: 435276 (The Pile)

Max Activating Token Index: 395

Text #4

Max Range: 1.1338. Min Range: -1.1338

Max Act: 0.8886. Min Act: -0.0000

Data Index: 595145 (The Pile)

Max Activating Token Index: 733

Text #5

Max Range: 1.1338. Min Range: -1.1338

Max Act: 0.9863. Min Act: -0.0000

Data Index: 459638 (The Pile)

Max Activating Token Index: 95

Text #6

Max Range: 1.1338. Min Range: -1.1338

Max Act: 0.9157. Min Act: -0.0000

Data Index: 26285 (The Pile)

Max Activating Token Index: 888

Text #7

Max Range: 1.1338. Min Range: -1.1338

Max Act: 0.8923. Min Act: -0.0000

Data Index: 1785690 (The Pile)

Max Activating Token Index: 963

Text #8

Max Range: 1.1338. Min Range: -1.1338

Max Act: 0.9210. Min Act: -0.0000

Data Index: 1441781 (The Pile)

Max Activating Token Index: 42

Text #9

Max Range: 1.1338. Min Range: -1.1338

Max Act: 0.8631. Min Act: -0.0000

Data Index: 1134033 (The Pile)

Max Activating Token Index: 909

Text #10

Max Range: 1.1338. Min Range: -1.1338

Max Act: 0.9309. Min Act: -0.0000

Data Index: 1870344 (The Pile)

Max Activating Token Index: 796

Text #11

Max Range: 1.1338. Min Range: -1.1338

Max Act: 0.9213. Min Act: -0.0000

Data Index: 386059 (The Pile)

Max Activating Token Index: 123

Text #12

Max Range: 1.1338. Min Range: -1.1338

Max Act: 0.8950. Min Act: -0.0000

Data Index: 1540693 (The Pile)

Max Activating Token Index: 737

Text #13

Max Range: 1.1338. Min Range: -1.1338

Max Act: 0.8923. Min Act: -0.0000

Data Index: 1502167 (The Pile)

Max Activating Token Index: 18

Text #14

Max Range: 1.1338. Min Range: -1.1338

Max Act: 0.8899. Min Act: -0.0000

Data Index: 1960160 (The Pile)

Max Activating Token Index: 285

Text #15

Max Range: 1.1338. Min Range: -1.1338

Max Act: 0.8412. Min Act: -0.0000

Data Index: 1732078 (The Pile)

Max Activating Token Index: 934

Text #16

Max Range: 1.1338. Min Range: -1.1338

Max Act: 0.8700. Min Act: -0.0000

Data Index: 1879007 (The Pile)

Max Activating Token Index: 845

Text #17

Max Range: 1.1338. Min Range: -1.1338

Max Act: 0.8826. Min Act: -0.0000

Data Index: 1014765 (The Pile)

Max Activating Token Index: 713

Text #18

Max Range: 1.1338. Min Range: -1.1338

Max Act: 0.8194. Min Act: -0.0000

Data Index: 536156 (The Pile)

Max Activating Token Index: 806

Text #19

Max Range: 1.1338. Min Range: -1.1338

Max Act: 0.8612. Min Act: -0.0000

Data Index: 657537 (The Pile)

Max Activating Token Index: 137