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

Dataset: The Pile

Neuron 316 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: 0.1575. Min Range: -0.1575

Max Act: 0.1477. Min Act: -0.0000

Data Index: 195118 (The Pile)

Max Activating Token Index: 811

Text #1

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1476. Min Act: -0.0000

Data Index: 644216 (The Pile)

Max Activating Token Index: 993

Text #2

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1575. Min Act: -0.0000

Data Index: 93749 (The Pile)

Max Activating Token Index: 603

Text #3

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1444. Min Act: -0.0000

Data Index: 1085515 (The Pile)

Max Activating Token Index: 492

Text #4

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1457. Min Act: -0.0000

Data Index: 1226481 (The Pile)

Max Activating Token Index: 996

Text #5

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1504. Min Act: -0.0000

Data Index: 1106869 (The Pile)

Max Activating Token Index: 932

Text #6

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1390. Min Act: -0.0000

Data Index: 1304570 (The Pile)

Max Activating Token Index: 522

Text #7

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1441. Min Act: -0.0000

Data Index: 1514709 (The Pile)

Max Activating Token Index: 224

Text #8

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1381. Min Act: -0.0000

Data Index: 697953 (The Pile)

Max Activating Token Index: 991

Text #9

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1450. Min Act: -0.0000

Data Index: 1046832 (The Pile)

Max Activating Token Index: 907

Text #10

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1266. Min Act: -0.0000

Data Index: 392137 (The Pile)

Max Activating Token Index: 671

Text #11

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1300. Min Act: -0.0000

Data Index: 202823 (The Pile)

Max Activating Token Index: 123

Text #12

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1296. Min Act: -0.0000

Data Index: 1004612 (The Pile)

Max Activating Token Index: 530

Text #13

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1279. Min Act: -0.0000

Data Index: 939193 (The Pile)

Max Activating Token Index: 928

Text #14

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1283. Min Act: -0.0000

Data Index: 762095 (The Pile)

Max Activating Token Index: 402

Text #15

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1361. Min Act: -0.0000

Data Index: 1857581 (The Pile)

Max Activating Token Index: 65

Text #16

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1309. Min Act: -0.0000

Data Index: 1446480 (The Pile)

Max Activating Token Index: 557

Text #17

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1263. Min Act: -0.0000

Data Index: 1643530 (The Pile)

Max Activating Token Index: 564

Text #18

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1273. Min Act: -0.0000

Data Index: 1346883 (The Pile)

Max Activating Token Index: 638

Text #19

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1276. Min Act: -0.0000

Data Index: 1456762 (The Pile)

Max Activating Token Index: 605