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

Dataset: The Pile

Neuron 3490 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: 1.2260. Min Range: -1.2260

Max Act: 1.1640. Min Act: -0.0000

Data Index: 438251 (The Pile)

Max Activating Token Index: 550

Text #1

Max Range: 1.2260. Min Range: -1.2260

Max Act: 1.2260. Min Act: -0.0000

Data Index: 264599 (The Pile)

Max Activating Token Index: 612

Text #2

Max Range: 1.2260. Min Range: -1.2260

Max Act: 1.1241. Min Act: -0.0000

Data Index: 195117 (The Pile)

Max Activating Token Index: 370

Text #3

Max Range: 1.2260. Min Range: -1.2260

Max Act: 1.0100. Min Act: -0.0000

Data Index: 396416 (The Pile)

Max Activating Token Index: 835

Text #4

Max Range: 1.2260. Min Range: -1.2260

Max Act: 1.0791. Min Act: -0.0000

Data Index: 1153475 (The Pile)

Max Activating Token Index: 354

Text #5

Max Range: 1.2260. Min Range: -1.2260

Max Act: 1.0741. Min Act: -0.0000

Data Index: 159384 (The Pile)

Max Activating Token Index: 214

Text #6

Max Range: 1.2260. Min Range: -1.2260

Max Act: 1.1410. Min Act: -0.0000

Data Index: 1902112 (The Pile)

Max Activating Token Index: 211

Text #7

Max Range: 1.2260. Min Range: -1.2260

Max Act: 1.0399. Min Act: -0.0000

Data Index: 254117 (The Pile)

Max Activating Token Index: 357

Text #8

Max Range: 1.2260. Min Range: -1.2260

Max Act: 1.1202. Min Act: -0.0000

Data Index: 630495 (The Pile)

Max Activating Token Index: 790

Text #9

Max Range: 1.2260. Min Range: -1.2260

Max Act: 0.8982. Min Act: -0.0000

Data Index: 1391632 (The Pile)

Max Activating Token Index: 987

Text #10

Max Range: 1.2260. Min Range: -1.2260

Max Act: 1.0320. Min Act: -0.0000

Data Index: 913432 (The Pile)

Max Activating Token Index: 105

Text #11

Max Range: 1.2260. Min Range: -1.2260

Max Act: 1.0533. Min Act: -0.0000

Data Index: 505022 (The Pile)

Max Activating Token Index: 235

Text #12

Max Range: 1.2260. Min Range: -1.2260

Max Act: 1.0704. Min Act: -0.0000

Data Index: 473664 (The Pile)

Max Activating Token Index: 813

Text #13

Max Range: 1.2260. Min Range: -1.2260

Max Act: 0.9689. Min Act: -0.0000

Data Index: 824703 (The Pile)

Max Activating Token Index: 76

Text #14

Max Range: 1.2260. Min Range: -1.2260

Max Act: 0.9625. Min Act: -0.0000

Data Index: 1612792 (The Pile)

Max Activating Token Index: 823

Text #15

Max Range: 1.2260. Min Range: -1.2260

Max Act: 0.9583. Min Act: -0.0000

Data Index: 911711 (The Pile)

Max Activating Token Index: 665

Text #16

Max Range: 1.2260. Min Range: -1.2260

Max Act: 0.9881. Min Act: -0.0000

Data Index: 676469 (The Pile)

Max Activating Token Index: 410

Text #17

Max Range: 1.2260. Min Range: -1.2260

Max Act: 0.9252. Min Act: -0.0000

Data Index: 479037 (The Pile)

Max Activating Token Index: 150

Text #18

Max Range: 1.2260. Min Range: -1.2260

Max Act: 0.9191. Min Act: -0.0000

Data Index: 1504056 (The Pile)

Max Activating Token Index: 660

Text #19

Max Range: 1.2260. Min Range: -1.2260

Max Act: 0.8876. Min Act: -0.0000

Data Index: 703320 (The Pile)

Max Activating Token Index: 981