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

Dataset: The Pile

Neuron 2356 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.2031. Min Act: -0.0000

Data Index: 1117391 (The Pile)

Max Activating Token Index: 368

Text #1

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1726. Min Act: -0.0000

Data Index: 930316 (The Pile)

Max Activating Token Index: 141

Text #2

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1821. Min Act: -0.0000

Data Index: 1727513 (The Pile)

Max Activating Token Index: 215

Text #3

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1511. Min Act: -0.0000

Data Index: 1185556 (The Pile)

Max Activating Token Index: 312

Text #4

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1601. Min Act: -0.0000

Data Index: 49479 (The Pile)

Max Activating Token Index: 77

Text #5

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1477. Min Act: -0.0000

Data Index: 1459569 (The Pile)

Max Activating Token Index: 427

Text #6

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1525. Min Act: -0.0000

Data Index: 1171650 (The Pile)

Max Activating Token Index: 831

Text #7

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1564. Min Act: -0.0000

Data Index: 596792 (The Pile)

Max Activating Token Index: 42

Text #8

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1356. Min Act: -0.0000

Data Index: 488633 (The Pile)

Max Activating Token Index: 832

Text #9

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1450. Min Act: -0.0000

Data Index: 777330 (The Pile)

Max Activating Token Index: 84

Text #10

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1501. Min Act: -0.0000

Data Index: 1680659 (The Pile)

Max Activating Token Index: 400

Text #11

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1459. Min Act: -0.0000

Data Index: 1710726 (The Pile)

Max Activating Token Index: 126

Text #12

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1442. Min Act: -0.0000

Data Index: 837766 (The Pile)

Max Activating Token Index: 791

Text #13

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1463. Min Act: -0.0000

Data Index: 1064550 (The Pile)

Max Activating Token Index: 818

Text #14

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1389. Min Act: -0.0000

Data Index: 1418425 (The Pile)

Max Activating Token Index: 715

Text #15

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1350. Min Act: -0.0000

Data Index: 982358 (The Pile)

Max Activating Token Index: 715

Text #16

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1383. Min Act: -0.0000

Data Index: 165987 (The Pile)

Max Activating Token Index: 266

Text #17

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1160. Min Act: -0.0000

Data Index: 270882 (The Pile)

Max Activating Token Index: 72

Text #18

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1325. Min Act: -0.0000

Data Index: 1433522 (The Pile)

Max Activating Token Index: 577

Text #19

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1278. Min Act: -0.0000

Data Index: 1924742 (The Pile)

Max Activating Token Index: 161