Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 345 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.2052. Min Act: -0.0001

Data Index: 1653480 (Python Code)

Max Activating Token Index: 711

Text #1

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1953. Min Act: -0.0001

Data Index: 1379294 (Python Code)

Max Activating Token Index: 872

Text #2

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1798. Min Act: -0.0001

Data Index: 1377526 (Python Code)

Max Activating Token Index: 710

Text #3

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1625. Min Act: -0.0001

Data Index: 1511507 (Python Code)

Max Activating Token Index: 945

Text #4

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1589. Min Act: -0.0001

Data Index: 1441087 (Python Code)

Max Activating Token Index: 413

Text #5

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1566. Min Act: -0.0000

Data Index: 1493101 (Python Code)

Max Activating Token Index: 543

Text #6

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1579. Min Act: -0.0001

Data Index: 1493496 (Python Code)

Max Activating Token Index: 159

Text #7

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1517. Min Act: -0.0001

Data Index: 1414430 (Python Code)

Max Activating Token Index: 812

Text #8

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1493. Min Act: -0.0001

Data Index: 1433091 (Python Code)

Max Activating Token Index: 35

Text #9

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1668. Min Act: -0.0001

Data Index: 1371239 (Python Code)

Max Activating Token Index: 374

Text #10

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1526. Min Act: -0.0001

Data Index: 1548195 (Python Code)

Max Activating Token Index: 52

Text #11

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1505. Min Act: -0.0001

Data Index: 1387000 (Python Code)

Max Activating Token Index: 191

Text #12

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1487. Min Act: -0.0001

Data Index: 1387817 (Python Code)

Max Activating Token Index: 785

Text #13

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1434. Min Act: -0.0001

Data Index: 1555673 (Python Code)

Max Activating Token Index: 205

Text #14

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1540. Min Act: -0.0001

Data Index: 1389641 (Python Code)

Max Activating Token Index: 578

Text #15

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1459. Min Act: -0.0001

Data Index: 1372091 (Python Code)

Max Activating Token Index: 126

Text #16

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1458. Min Act: -0.0001

Data Index: 1381697 (Python Code)

Max Activating Token Index: 402

Text #17

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1465. Min Act: -0.0001

Data Index: 1565830 (Python Code)

Max Activating Token Index: 961

Text #18

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1496. Min Act: -0.0001

Data Index: 1584493 (Python Code)

Max Activating Token Index: 767

Text #19

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1432. Min Act: -0.0001

Data Index: 1473529 (Python Code)

Max Activating Token Index: 354