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

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

Neuron 4718 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.5106. Min Act: -0.0000

Data Index: 1547465 (Python Code)

Max Activating Token Index: 956

Text #1

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.4527. Min Act: -0.0000

Data Index: 1495587 (Python Code)

Max Activating Token Index: 87

Text #2

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.3163. Min Act: -0.0000

Data Index: 1403161 (Python Code)

Max Activating Token Index: 102

Text #3

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.2390. Min Act: -0.0000

Data Index: 1457060 (Python Code)

Max Activating Token Index: 451

Text #4

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.2603. Min Act: -0.0000

Data Index: 1511608 (Python Code)

Max Activating Token Index: 84

Text #5

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.2211. Min Act: -0.0000

Data Index: 1577709 (Python Code)

Max Activating Token Index: 194

Text #6

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.1256. Min Act: -0.0000

Data Index: 1512434 (Python Code)

Max Activating Token Index: 384

Text #7

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.1713. Min Act: -0.0000

Data Index: 1395306 (Python Code)

Max Activating Token Index: 346

Text #8

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.1370. Min Act: -0.0000

Data Index: 1489402 (Python Code)

Max Activating Token Index: 713

Text #9

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.0951. Min Act: -0.0000

Data Index: 1426945 (Python Code)

Max Activating Token Index: 409

Text #10

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.1876. Min Act: -0.0000

Data Index: 1440855 (Python Code)

Max Activating Token Index: 521

Text #11

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.0779. Min Act: -0.0000

Data Index: 1604841 (Python Code)

Max Activating Token Index: 69

Text #12

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.0499. Min Act: -0.0000

Data Index: 1420801 (Python Code)

Max Activating Token Index: 146

Text #13

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.0113. Min Act: -0.0000

Data Index: 1439013 (Python Code)

Max Activating Token Index: 180

Text #14

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.0326. Min Act: -0.0000

Data Index: 1610737 (Python Code)

Max Activating Token Index: 384

Text #15

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.0351. Min Act: -0.0000

Data Index: 1591707 (Python Code)

Max Activating Token Index: 341

Text #16

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.0521. Min Act: -0.0000

Data Index: 1536968 (Python Code)

Max Activating Token Index: 659

Text #17

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.0410. Min Act: -0.0000

Data Index: 1463771 (Python Code)

Max Activating Token Index: 624

Text #18

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.0364. Min Act: -0.0000

Data Index: 1423533 (Python Code)

Max Activating Token Index: 170

Text #19

Max Range: 1.5106. Min Range: -1.5106

Max Act: 1.0056. Min Act: -0.0000

Data Index: 1636676 (Python Code)

Max Activating Token Index: 449