Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2947 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1562. Min Act: -0.0001

Data Index: 1655201 (Python Code)

Max Activating Token Index: 647

Text #1

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1595. Min Act: -0.0001

Data Index: 1492562 (Python Code)

Max Activating Token Index: 379

Text #2

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1532. Min Act: -0.0001

Data Index: 1463958 (Python Code)

Max Activating Token Index: 340

Text #3

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1470. Min Act: -0.0001

Data Index: 1397368 (Python Code)

Max Activating Token Index: 416

Text #4

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1522. Min Act: -0.0001

Data Index: 1583073 (Python Code)

Max Activating Token Index: 770

Text #5

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1489. Min Act: -0.0001

Data Index: 1624040 (Python Code)

Max Activating Token Index: 782

Text #6

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1491. Min Act: -0.0001

Data Index: 1551766 (Python Code)

Max Activating Token Index: 314

Text #7

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1426. Min Act: -0.0001

Data Index: 1465569 (Python Code)

Max Activating Token Index: 744

Text #8

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1438. Min Act: -0.0001

Data Index: 1364013 (Python Code)

Max Activating Token Index: 289

Text #9

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1448. Min Act: -0.0001

Data Index: 1467194 (Python Code)

Max Activating Token Index: 1019

Text #10

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1337. Min Act: -0.0001

Data Index: 1391851 (Python Code)

Max Activating Token Index: 715

Text #11

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1377. Min Act: -0.0001

Data Index: 1492944 (Python Code)

Max Activating Token Index: 139

Text #12

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1296. Min Act: -0.0001

Data Index: 1363671 (Python Code)

Max Activating Token Index: 14

Text #13

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1390. Min Act: -0.0001

Data Index: 1387471 (Python Code)

Max Activating Token Index: 166

Text #14

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1338. Min Act: -0.0001

Data Index: 1378213 (Python Code)

Max Activating Token Index: 245

Text #15

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1331. Min Act: -0.0001

Data Index: 1651387 (Python Code)

Max Activating Token Index: 448

Text #16

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1311. Min Act: -0.0001

Data Index: 1469963 (Python Code)

Max Activating Token Index: 416

Text #17

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1302. Min Act: -0.0001

Data Index: 1377662 (Python Code)

Max Activating Token Index: 61

Text #18

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1253. Min Act: -0.0001

Data Index: 1591628 (Python Code)

Max Activating Token Index: 111

Text #19

Max Range: 0.1595. Min Range: -0.1595

Max Act: 0.1289. Min Act: -0.0001

Data Index: 1585342 (Python Code)

Max Activating Token Index: 956