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

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

Neuron 1300 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1367. Min Range: -1.1367

Max Act: 1.1268. Min Act: -0.0001

Data Index: 1538837 (Python Code)

Max Activating Token Index: 605

Text #1

Max Range: 1.1367. Min Range: -1.1367

Max Act: 1.1309. Min Act: -0.0001

Data Index: 1481764 (Python Code)

Max Activating Token Index: 843

Text #2

Max Range: 1.1367. Min Range: -1.1367

Max Act: 1.0211. Min Act: -0.0001

Data Index: 1634580 (Python Code)

Max Activating Token Index: 117

Text #3

Max Range: 1.1367. Min Range: -1.1367

Max Act: 1.0154. Min Act: -0.0000

Data Index: 1370673 (Python Code)

Max Activating Token Index: 392

Text #4

Max Range: 1.1367. Min Range: -1.1367

Max Act: 1.0466. Min Act: -0.0000

Data Index: 1596124 (Python Code)

Max Activating Token Index: 514

Text #5

Max Range: 1.1367. Min Range: -1.1367

Max Act: 1.1367. Min Act: -0.0001

Data Index: 1645733 (Python Code)

Max Activating Token Index: 239

Text #6

Max Range: 1.1367. Min Range: -1.1367

Max Act: 1.0296. Min Act: -0.0000

Data Index: 1551084 (Python Code)

Max Activating Token Index: 167

Text #7

Max Range: 1.1367. Min Range: -1.1367

Max Act: 0.8641. Min Act: -0.0000

Data Index: 1633513 (Python Code)

Max Activating Token Index: 608

Text #8

Max Range: 1.1367. Min Range: -1.1367

Max Act: 0.9955. Min Act: -0.0000

Data Index: 1555400 (Python Code)

Max Activating Token Index: 146

Text #9

Max Range: 1.1367. Min Range: -1.1367

Max Act: 1.0822. Min Act: -0.0001

Data Index: 1550077 (Python Code)

Max Activating Token Index: 656

Text #10

Max Range: 1.1367. Min Range: -1.1367

Max Act: 1.0474. Min Act: -0.0000

Data Index: 1648613 (Python Code)

Max Activating Token Index: 451

Text #11

Max Range: 1.1367. Min Range: -1.1367

Max Act: 1.0147. Min Act: -0.0000

Data Index: 1397883 (Python Code)

Max Activating Token Index: 231

Text #12

Max Range: 1.1367. Min Range: -1.1367

Max Act: 1.0108. Min Act: -0.0001

Data Index: 1548489 (Python Code)

Max Activating Token Index: 47

Text #13

Max Range: 1.1367. Min Range: -1.1367

Max Act: 0.9981. Min Act: -0.0001

Data Index: 1653602 (Python Code)

Max Activating Token Index: 746

Text #14

Max Range: 1.1367. Min Range: -1.1367

Max Act: 0.9686. Min Act: -0.0000

Data Index: 1375063 (Python Code)

Max Activating Token Index: 124

Text #15

Max Range: 1.1367. Min Range: -1.1367

Max Act: 0.9626. Min Act: -0.0001

Data Index: 1559230 (Python Code)

Max Activating Token Index: 603

Text #16

Max Range: 1.1367. Min Range: -1.1367

Max Act: 0.9744. Min Act: -0.0001

Data Index: 1378607 (Python Code)

Max Activating Token Index: 462

Text #17

Max Range: 1.1367. Min Range: -1.1367

Max Act: 0.9373. Min Act: -0.0001

Data Index: 1632390 (Python Code)

Max Activating Token Index: 296

Text #18

Max Range: 1.1367. Min Range: -1.1367

Max Act: 0.9660. Min Act: -0.0001

Data Index: 1613883 (Python Code)

Max Activating Token Index: 568

Text #19

Max Range: 1.1367. Min Range: -1.1367

Max Act: 0.9132. Min Act: -0.0001

Data Index: 1366056 (Python Code)

Max Activating Token Index: 128