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

Dataset: The Pile

Neuron 2488 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.2094. Min Act: -0.0000

Data Index: 641833 (The Pile)

Max Activating Token Index: 506

Text #1

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1577. Min Act: -0.0000

Data Index: 1443115 (The Pile)

Max Activating Token Index: 348

Text #2

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1520. Min Act: -0.0000

Data Index: 978484 (The Pile)

Max Activating Token Index: 85

Text #3

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1526. Min Act: -0.0000

Data Index: 1329671 (The Pile)

Max Activating Token Index: 619

Text #4

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1559. Min Act: -0.0000

Data Index: 1004276 (The Pile)

Max Activating Token Index: 342

Text #5

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1454. Min Act: -0.0000

Data Index: 1041009 (The Pile)

Max Activating Token Index: 387

Text #6

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1420. Min Act: -0.0000

Data Index: 404165 (The Pile)

Max Activating Token Index: 184

Text #7

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1354. Min Act: -0.0000

Data Index: 292453 (The Pile)

Max Activating Token Index: 521

Text #8

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1447. Min Act: -0.0000

Data Index: 970138 (The Pile)

Max Activating Token Index: 99

Text #9

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1386. Min Act: -0.0000

Data Index: 534327 (The Pile)

Max Activating Token Index: 184

Text #10

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1398. Min Act: -0.0000

Data Index: 94681 (The Pile)

Max Activating Token Index: 128

Text #11

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1291. Min Act: -0.0000

Data Index: 1376346 (The Pile)

Max Activating Token Index: 760

Text #12

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1434. Min Act: -0.0000

Data Index: 939916 (The Pile)

Max Activating Token Index: 229

Text #13

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1377. Min Act: -0.0000

Data Index: 1401237 (The Pile)

Max Activating Token Index: 504

Text #14

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1303. Min Act: -0.0000

Data Index: 730252 (The Pile)

Max Activating Token Index: 377

Text #15

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1382. Min Act: -0.0000

Data Index: 1887034 (The Pile)

Max Activating Token Index: 165

Text #16

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1230. Min Act: -0.0000

Data Index: 1423348 (The Pile)

Max Activating Token Index: 709

Text #17

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1279. Min Act: -0.0000

Data Index: 1755688 (The Pile)

Max Activating Token Index: 315

Text #18

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1316. Min Act: -0.0000

Data Index: 1179766 (The Pile)

Max Activating Token Index: 120

Text #19

Max Range: 0.2094. Min Range: -0.2094

Max Act: 0.1241. Min Act: -0.0000

Data Index: 738498 (The Pile)

Max Activating Token Index: 507