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

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

Neuron 4666 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: 1.2329. Min Range: -1.2329

Max Act: 1.2329. Min Act: -0.0000

Data Index: 1363094 (Python Code)

Max Activating Token Index: 953

Text #1

Max Range: 1.2329. Min Range: -1.2329

Max Act: 1.1532. Min Act: -0.0000

Data Index: 1384938 (Python Code)

Max Activating Token Index: 383

Text #2

Max Range: 1.2329. Min Range: -1.2329

Max Act: 1.1387. Min Act: -0.0000

Data Index: 1583464 (Python Code)

Max Activating Token Index: 816

Text #3

Max Range: 1.2329. Min Range: -1.2329

Max Act: 1.1474. Min Act: -0.0000

Data Index: 1609529 (Python Code)

Max Activating Token Index: 937

Text #4

Max Range: 1.2329. Min Range: -1.2329

Max Act: 1.1355. Min Act: -0.0000

Data Index: 1598794 (Python Code)

Max Activating Token Index: 16

Text #5

Max Range: 1.2329. Min Range: -1.2329

Max Act: 1.1081. Min Act: -0.0000

Data Index: 1564460 (Python Code)

Max Activating Token Index: 520

Text #6

Max Range: 1.2329. Min Range: -1.2329

Max Act: 1.0986. Min Act: -0.0000

Data Index: 1634667 (Python Code)

Max Activating Token Index: 656

Text #7

Max Range: 1.2329. Min Range: -1.2329

Max Act: 1.1442. Min Act: -0.0000

Data Index: 1623292 (Python Code)

Max Activating Token Index: 864

Text #8

Max Range: 1.2329. Min Range: -1.2329

Max Act: 1.1544. Min Act: -0.0000

Data Index: 1384270 (Python Code)

Max Activating Token Index: 896

Text #9

Max Range: 1.2329. Min Range: -1.2329

Max Act: 1.1128. Min Act: -0.0000

Data Index: 1408526 (Python Code)

Max Activating Token Index: 611

Text #10

Max Range: 1.2329. Min Range: -1.2329

Max Act: 1.0999. Min Act: -0.0000

Data Index: 1503710 (Python Code)

Max Activating Token Index: 36

Text #11

Max Range: 1.2329. Min Range: -1.2329

Max Act: 1.0915. Min Act: -0.0000

Data Index: 1617937 (Python Code)

Max Activating Token Index: 940

Text #12

Max Range: 1.2329. Min Range: -1.2329

Max Act: 1.1319. Min Act: -0.0000

Data Index: 1462711 (Python Code)

Max Activating Token Index: 185

Text #13

Max Range: 1.2329. Min Range: -1.2329

Max Act: 1.1229. Min Act: -0.0000

Data Index: 1570484 (Python Code)

Max Activating Token Index: 981

Text #14

Max Range: 1.2329. Min Range: -1.2329

Max Act: 1.0605. Min Act: -0.0000

Data Index: 1526331 (Python Code)

Max Activating Token Index: 466

Text #15

Max Range: 1.2329. Min Range: -1.2329

Max Act: 1.1170. Min Act: -0.0000

Data Index: 1596516 (Python Code)

Max Activating Token Index: 787

Text #16

Max Range: 1.2329. Min Range: -1.2329

Max Act: 1.0641. Min Act: -0.0000

Data Index: 1656587 (Python Code)

Max Activating Token Index: 428

Text #17

Max Range: 1.2329. Min Range: -1.2329

Max Act: 1.0567. Min Act: -0.0000

Data Index: 1459604 (Python Code)

Max Activating Token Index: 634

Text #18

Max Range: 1.2329. Min Range: -1.2329

Max Act: 1.0479. Min Act: -0.0000

Data Index: 1529146 (Python Code)

Max Activating Token Index: 374

Text #19

Max Range: 1.2329. Min Range: -1.2329

Max Act: 1.0509. Min Act: -0.0000

Data Index: 1592855 (Python Code)

Max Activating Token Index: 28