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

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

Neuron 1026 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: 0.2118. Min Range: -0.2118

Max Act: 0.2083. Min Act: -0.0001

Data Index: 1546358 (Python Code)

Max Activating Token Index: 271

Text #1

Max Range: 0.2118. Min Range: -0.2118

Max Act: 0.2118. Min Act: -0.0000

Data Index: 1375894 (Python Code)

Max Activating Token Index: 292

Text #2

Max Range: 0.2118. Min Range: -0.2118

Max Act: 0.1948. Min Act: -0.0001

Data Index: 1464634 (Python Code)

Max Activating Token Index: 27

Text #3

Max Range: 0.2118. Min Range: -0.2118

Max Act: 0.1970. Min Act: -0.0000

Data Index: 1526514 (Python Code)

Max Activating Token Index: 212

Text #4

Max Range: 0.2118. Min Range: -0.2118

Max Act: 0.2030. Min Act: -0.0000

Data Index: 1615379 (Python Code)

Max Activating Token Index: 191

Text #5

Max Range: 0.2118. Min Range: -0.2118

Max Act: 0.1775. Min Act: -0.0000

Data Index: 1520560 (Python Code)

Max Activating Token Index: 152

Text #6

Max Range: 0.2118. Min Range: -0.2118

Max Act: 0.1774. Min Act: -0.0000

Data Index: 1375332 (Python Code)

Max Activating Token Index: 446

Text #7

Max Range: 0.2118. Min Range: -0.2118

Max Act: 0.1761. Min Act: -0.0000

Data Index: 1597255 (Python Code)

Max Activating Token Index: 327

Text #8

Max Range: 0.2118. Min Range: -0.2118

Max Act: 0.1676. Min Act: -0.0000

Data Index: 1443924 (Python Code)

Max Activating Token Index: 487

Text #9

Max Range: 0.2118. Min Range: -0.2118

Max Act: 0.1796. Min Act: -0.0001

Data Index: 1596099 (Python Code)

Max Activating Token Index: 605

Text #10

Max Range: 0.2118. Min Range: -0.2118

Max Act: 0.1682. Min Act: -0.0001

Data Index: 1623714 (Python Code)

Max Activating Token Index: 198

Text #11

Max Range: 0.2118. Min Range: -0.2118

Max Act: 0.1486. Min Act: -0.0000

Data Index: 1436671 (Python Code)

Max Activating Token Index: 184

Text #12

Max Range: 0.2118. Min Range: -0.2118

Max Act: 0.1476. Min Act: -0.0001

Data Index: 1415400 (Python Code)

Max Activating Token Index: 219

Text #13

Max Range: 0.2118. Min Range: -0.2118

Max Act: 0.1369. Min Act: -0.0000

Data Index: 1577791 (Python Code)

Max Activating Token Index: 71

Text #14

Max Range: 0.2118. Min Range: -0.2118

Max Act: 0.1434. Min Act: -0.0000

Data Index: 1620656 (Python Code)

Max Activating Token Index: 720

Text #15

Max Range: 0.2118. Min Range: -0.2118

Max Act: 0.1416. Min Act: -0.0000

Data Index: 1510523 (Python Code)

Max Activating Token Index: 31

Text #16

Max Range: 0.2118. Min Range: -0.2118

Max Act: 0.1451. Min Act: -0.0000

Data Index: 1480361 (Python Code)

Max Activating Token Index: 297

Text #17

Max Range: 0.2118. Min Range: -0.2118

Max Act: 0.1409. Min Act: -0.0001

Data Index: 1598705 (Python Code)

Max Activating Token Index: 289

Text #18

Max Range: 0.2118. Min Range: -0.2118

Max Act: 0.1317. Min Act: -0.0001

Data Index: 1481632 (Python Code)

Max Activating Token Index: 85

Text #19

Max Range: 0.2118. Min Range: -0.2118

Max Act: 0.1262. Min Act: -0.0000

Data Index: 1519372 (Python Code)

Max Activating Token Index: 192