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

Dataset: The Pile

Neuron 1473 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1434. Min Range: -0.1434

Max Act: 0.1434. Min Act: 0.0000

Data Index: 1815472 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1434. Min Range: -0.1434

Max Act: 0.1379. Min Act: 0.0000

Data Index: 1908477 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1434. Min Range: -0.1434

Max Act: 0.1369. Min Act: -0.0000

Data Index: 1759620 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1434. Min Range: -0.1434

Max Act: 0.1345. Min Act: 0.0000

Data Index: 1143248 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1434. Min Range: -0.1434

Max Act: 0.1328. Min Act: -0.0000

Data Index: 261862 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1434. Min Range: -0.1434

Max Act: 0.1330. Min Act: -0.0000

Data Index: 1762041 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1434. Min Range: -0.1434

Max Act: 0.1323. Min Act: -0.0000

Data Index: 404493 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.1434. Min Range: -0.1434

Max Act: 0.1313. Min Act: -0.0000

Data Index: 79203 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1434. Min Range: -0.1434

Max Act: 0.1310. Min Act: -0.0000

Data Index: 1310764 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.1434. Min Range: -0.1434

Max Act: 0.1348. Min Act: -0.0000

Data Index: 1153645 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.1434. Min Range: -0.1434

Max Act: 0.1344. Min Act: -0.0000

Data Index: 68621 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.1434. Min Range: -0.1434

Max Act: 0.1296. Min Act: -0.0000

Data Index: 555698 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.1434. Min Range: -0.1434

Max Act: 0.1291. Min Act: 0.0000

Data Index: 745595 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.1434. Min Range: -0.1434

Max Act: 0.1338. Min Act: -0.0000

Data Index: 179222 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.1434. Min Range: -0.1434

Max Act: 0.1280. Min Act: -0.0000

Data Index: 128737 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.1434. Min Range: -0.1434

Max Act: 0.1280. Min Act: -0.0000

Data Index: 1917715 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1434. Min Range: -0.1434

Max Act: 0.1265. Min Act: -0.0000

Data Index: 1644139 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.1434. Min Range: -0.1434

Max Act: 0.1254. Min Act: -0.0000

Data Index: 1479008 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.1434. Min Range: -0.1434

Max Act: 0.1257. Min Act: -0.0000

Data Index: 1596305 (The Pile)

Max Activating Token Index: 3

Text #19

Max Range: 0.1434. Min Range: -0.1434

Max Act: 0.1255. Min Act: 0.0000

Data Index: 449526 (The Pile)

Max Activating Token Index: 550