Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5056 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1765. Min Act: -0.0001

Data Index: 420112 (C4 (Web Text))

Max Activating Token Index: 623

Text #1

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1455. Min Act: -0.0001

Data Index: 1242561 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1389. Min Act: -0.0001

Data Index: 1201072 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1378. Min Act: -0.0001

Data Index: 365167 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1495. Min Act: -0.0001

Data Index: 627543 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1460. Min Act: -0.0001

Data Index: 330392 (C4 (Web Text))

Max Activating Token Index: 256

Text #6

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1444. Min Act: -0.0001

Data Index: 566735 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1490. Min Act: -0.0001

Data Index: 455740 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1385. Min Act: -0.0002

Data Index: 468436 (C4 (Web Text))

Max Activating Token Index: 7

Text #9

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1419. Min Act: -0.0001

Data Index: 1161962 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1432. Min Act: -0.0001

Data Index: 1179845 (C4 (Web Text))

Max Activating Token Index: 88

Text #11

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1368. Min Act: -0.0001

Data Index: 218039 (C4 (Web Text))

Max Activating Token Index: 456

Text #12

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1358. Min Act: -0.0001

Data Index: 676720 (C4 (Web Text))

Max Activating Token Index: 504

Text #13

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1350. Min Act: -0.0001

Data Index: 37376 (C4 (Web Text))

Max Activating Token Index: 296

Text #14

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1446. Min Act: -0.0001

Data Index: 79707 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1387. Min Act: -0.0001

Data Index: 319667 (C4 (Web Text))

Max Activating Token Index: 146

Text #16

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1422. Min Act: -0.0001

Data Index: 434899 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1428. Min Act: -0.0001

Data Index: 67475 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1371. Min Act: -0.0001

Data Index: 403144 (C4 (Web Text))

Max Activating Token Index: 272

Text #19

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1415. Min Act: -0.0001

Data Index: 971312 (C4 (Web Text))

Max Activating Token Index: 518