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

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

Neuron 394 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.2048. Min Act: -0.0000

Data Index: 1238348 (C4 (Web Text))

Max Activating Token Index: 865

Text #1

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1855. Min Act: -0.0000

Data Index: 565462 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1621. Min Act: -0.0000

Data Index: 33749 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1536. Min Act: -0.0000

Data Index: 963613 (C4 (Web Text))

Max Activating Token Index: 733

Text #4

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1631. Min Act: -0.0000

Data Index: 177529 (C4 (Web Text))

Max Activating Token Index: 634

Text #5

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1465. Min Act: -0.0000

Data Index: 655426 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1491. Min Act: -0.0000

Data Index: 448677 (C4 (Web Text))

Max Activating Token Index: 455

Text #7

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1598. Min Act: -0.0000

Data Index: 1271695 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1488. Min Act: -0.0000

Data Index: 448310 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1470. Min Act: -0.0000

Data Index: 1144451 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1403. Min Act: -0.0000

Data Index: 730925 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1452. Min Act: -0.0000

Data Index: 706614 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1426. Min Act: -0.0000

Data Index: 1074618 (C4 (Web Text))

Max Activating Token Index: 646

Text #13

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1349. Min Act: -0.0000

Data Index: 1343888 (C4 (Web Text))

Max Activating Token Index: 496

Text #14

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1338. Min Act: -0.0000

Data Index: 449902 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1328. Min Act: -0.0000

Data Index: 94769 (C4 (Web Text))

Max Activating Token Index: 512

Text #16

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1293. Min Act: -0.0000

Data Index: 4893 (C4 (Web Text))

Max Activating Token Index: 506

Text #17

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1241. Min Act: -0.0000

Data Index: 1280396 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1282. Min Act: -0.0000

Data Index: 757786 (C4 (Web Text))

Max Activating Token Index: 658

Text #19

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1323. Min Act: -0.0000

Data Index: 725932 (C4 (Web Text))

Max Activating Token Index: 808