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

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

Neuron 2016 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0450. Min Act: -0.0000

Data Index: 1634796 (Python Code)

Max Activating Token Index: 80

Text #1

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0368. Min Act: -0.0000

Data Index: 1599104 (Python Code)

Max Activating Token Index: 711

Text #2

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0352. Min Act: -0.0000

Data Index: 1466007 (Python Code)

Max Activating Token Index: 745

Text #3

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0357. Min Act: -0.0000

Data Index: 1433262 (Python Code)

Max Activating Token Index: 996

Text #4

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0343. Min Act: 0.0000

Data Index: 1381652 (Python Code)

Max Activating Token Index: 691

Text #5

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0351. Min Act: -0.0000

Data Index: 1396932 (Python Code)

Max Activating Token Index: 144

Text #6

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0362. Min Act: -0.0000

Data Index: 1625895 (Python Code)

Max Activating Token Index: 639

Text #7

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0343. Min Act: -0.0001

Data Index: 1621031 (Python Code)

Max Activating Token Index: 535

Text #8

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0352. Min Act: -0.0000

Data Index: 1398060 (Python Code)

Max Activating Token Index: 1018

Text #9

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0338. Min Act: -0.0000

Data Index: 1530862 (Python Code)

Max Activating Token Index: 789

Text #10

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0337. Min Act: -0.0000

Data Index: 1471712 (Python Code)

Max Activating Token Index: 820

Text #11

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0328. Min Act: -0.0001

Data Index: 1036484 (C4 (Web Text))

Max Activating Token Index: 392

Text #12

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0333. Min Act: -0.0000

Data Index: 1647102 (Python Code)

Max Activating Token Index: 586

Text #13

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0309. Min Act: -0.0000

Data Index: 293090 (C4 (Web Text))

Max Activating Token Index: 571

Text #14

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0333. Min Act: -0.0001

Data Index: 1459818 (Python Code)

Max Activating Token Index: 987

Text #15

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0330. Min Act: 0.0000

Data Index: 1502110 (Python Code)

Max Activating Token Index: 662

Text #16

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0329. Min Act: -0.0000

Data Index: 1621838 (Python Code)

Max Activating Token Index: 394

Text #17

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0324. Min Act: -0.0000

Data Index: 1621884 (Python Code)

Max Activating Token Index: 728

Text #18

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0335. Min Act: -0.0001

Data Index: 143241 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0310. Min Act: -0.0000

Data Index: 1529369 (Python Code)

Max Activating Token Index: 877