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

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

Neuron 1587 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.4500. Min Range: -1.4500

Max Act: 1.4500. Min Act: -0.0001

Data Index: 1399302 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 1.4500. Min Range: -1.4500

Max Act: 1.1851. Min Act: -0.0001

Data Index: 1545994 (Python Code)

Max Activating Token Index: 6

Text #2

Max Range: 1.4500. Min Range: -1.4500

Max Act: 1.1617. Min Act: -0.0001

Data Index: 1562129 (Python Code)

Max Activating Token Index: 572

Text #3

Max Range: 1.4500. Min Range: -1.4500

Max Act: 1.1787. Min Act: -0.0001

Data Index: 1501911 (Python Code)

Max Activating Token Index: 16

Text #4

Max Range: 1.4500. Min Range: -1.4500

Max Act: 1.1541. Min Act: -0.0001

Data Index: 1529289 (Python Code)

Max Activating Token Index: 20

Text #5

Max Range: 1.4500. Min Range: -1.4500

Max Act: 1.1531. Min Act: -0.0001

Data Index: 1413334 (Python Code)

Max Activating Token Index: 6

Text #6

Max Range: 1.4500. Min Range: -1.4500

Max Act: 1.1375. Min Act: -0.0001

Data Index: 1376332 (Python Code)

Max Activating Token Index: 6

Text #7

Max Range: 1.4500. Min Range: -1.4500

Max Act: 1.1531. Min Act: -0.0001

Data Index: 1525242 (Python Code)

Max Activating Token Index: 768

Text #8

Max Range: 1.4500. Min Range: -1.4500

Max Act: 1.1300. Min Act: -0.0001

Data Index: 1590405 (Python Code)

Max Activating Token Index: 41

Text #9

Max Range: 1.4500. Min Range: -1.4500

Max Act: 1.1244. Min Act: -0.0002

Data Index: 1365468 (Python Code)

Max Activating Token Index: 7

Text #10

Max Range: 1.4500. Min Range: -1.4500

Max Act: 1.1251. Min Act: -0.0001

Data Index: 1398380 (Python Code)

Max Activating Token Index: 643

Text #11

Max Range: 1.4500. Min Range: -1.4500

Max Act: 1.1159. Min Act: -0.0001

Data Index: 1383720 (Python Code)

Max Activating Token Index: 71

Text #12

Max Range: 1.4500. Min Range: -1.4500

Max Act: 1.1056. Min Act: -0.0001

Data Index: 1573993 (Python Code)

Max Activating Token Index: 14

Text #13

Max Range: 1.4500. Min Range: -1.4500

Max Act: 1.1132. Min Act: -0.0001

Data Index: 1482825 (Python Code)

Max Activating Token Index: 84

Text #14

Max Range: 1.4500. Min Range: -1.4500

Max Act: 1.1034. Min Act: -0.0001

Data Index: 1458540 (Python Code)

Max Activating Token Index: 502

Text #15

Max Range: 1.4500. Min Range: -1.4500

Max Act: 1.0687. Min Act: -0.0001

Data Index: 1429626 (Python Code)

Max Activating Token Index: 47

Text #16

Max Range: 1.4500. Min Range: -1.4500

Max Act: 1.0858. Min Act: -0.0001

Data Index: 1544475 (Python Code)

Max Activating Token Index: 268

Text #17

Max Range: 1.4500. Min Range: -1.4500

Max Act: 1.0736. Min Act: -0.0001

Data Index: 1445571 (Python Code)

Max Activating Token Index: 419

Text #18

Max Range: 1.4500. Min Range: -1.4500

Max Act: 1.0790. Min Act: -0.0001

Data Index: 1368115 (Python Code)

Max Activating Token Index: 382

Text #19

Max Range: 1.4500. Min Range: -1.4500

Max Act: 1.0664. Min Act: -0.0001

Data Index: 1589136 (Python Code)

Max Activating Token Index: 749