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

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

Neuron 3949 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1580. Min Act: -0.0000

Data Index: 1402196 (Python Code)

Max Activating Token Index: 150

Text #1

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1586. Min Act: -0.0000

Data Index: 1368061 (Python Code)

Max Activating Token Index: 90

Text #2

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1552. Min Act: -0.0000

Data Index: 1590443 (Python Code)

Max Activating Token Index: 11

Text #3

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1515. Min Act: -0.0000

Data Index: 1377021 (Python Code)

Max Activating Token Index: 14

Text #4

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1400. Min Act: -0.0000

Data Index: 1416008 (Python Code)

Max Activating Token Index: 34

Text #5

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1509. Min Act: -0.0000

Data Index: 1440530 (Python Code)

Max Activating Token Index: 20

Text #6

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1448. Min Act: -0.0000

Data Index: 1527078 (Python Code)

Max Activating Token Index: 49

Text #7

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1367. Min Act: -0.0000

Data Index: 1416680 (Python Code)

Max Activating Token Index: 29

Text #8

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1471. Min Act: -0.0000

Data Index: 1583860 (Python Code)

Max Activating Token Index: 68

Text #9

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1312. Min Act: -0.0000

Data Index: 1590614 (Python Code)

Max Activating Token Index: 359

Text #10

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1318. Min Act: -0.0000

Data Index: 1105572 (C4 (Web Text))

Max Activating Token Index: 245

Text #11

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1410. Min Act: -0.0000

Data Index: 1159756 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1340. Min Act: -0.0000

Data Index: 1627909 (Python Code)

Max Activating Token Index: 12

Text #13

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1435. Min Act: -0.0000

Data Index: 1491621 (Python Code)

Max Activating Token Index: 136

Text #14

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1329. Min Act: -0.0000

Data Index: 1365215 (Python Code)

Max Activating Token Index: 44

Text #15

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1374. Min Act: -0.0000

Data Index: 1402980 (Python Code)

Max Activating Token Index: 190

Text #16

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1326. Min Act: -0.0000

Data Index: 1616729 (Python Code)

Max Activating Token Index: 5

Text #17

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1328. Min Act: -0.0000

Data Index: 1478905 (Python Code)

Max Activating Token Index: 83

Text #18

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1257. Min Act: -0.0000

Data Index: 1601898 (Python Code)

Max Activating Token Index: 3

Text #19

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1298. Min Act: -0.0000

Data Index: 1449427 (Python Code)

Max Activating Token Index: 95