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

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

Neuron 1838 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.3379. Min Act: -0.0001

Data Index: 1517980 (Python Code)

Max Activating Token Index: 996

Text #1

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.4104. Min Act: -0.0001

Data Index: 1509564 (Python Code)

Max Activating Token Index: 774

Text #2

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.2356. Min Act: -0.0001

Data Index: 1654070 (Python Code)

Max Activating Token Index: 398

Text #3

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.2316. Min Act: -0.0001

Data Index: 1614636 (Python Code)

Max Activating Token Index: 250

Text #4

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.2031. Min Act: -0.0001

Data Index: 1471762 (Python Code)

Max Activating Token Index: 729

Text #5

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.2042. Min Act: -0.0001

Data Index: 1467516 (Python Code)

Max Activating Token Index: 509

Text #6

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.1864. Min Act: -0.0001

Data Index: 1633581 (Python Code)

Max Activating Token Index: 504

Text #7

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.0985. Min Act: -0.0001

Data Index: 1614765 (Python Code)

Max Activating Token Index: 886

Text #8

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.1032. Min Act: -0.0001

Data Index: 1627261 (Python Code)

Max Activating Token Index: 408

Text #9

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.1506. Min Act: -0.0001

Data Index: 1435774 (Python Code)

Max Activating Token Index: 292

Text #10

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.0652. Min Act: -0.0001

Data Index: 1395556 (Python Code)

Max Activating Token Index: 41

Text #11

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.0899. Min Act: -0.0001

Data Index: 1397581 (Python Code)

Max Activating Token Index: 195

Text #12

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.0196. Min Act: -0.0001

Data Index: 1411564 (Python Code)

Max Activating Token Index: 162

Text #13

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.0385. Min Act: -0.0001

Data Index: 1510681 (Python Code)

Max Activating Token Index: 171

Text #14

Max Range: 1.4104. Min Range: -1.4104

Max Act: 0.9719. Min Act: -0.0001

Data Index: 1404288 (Python Code)

Max Activating Token Index: 789

Text #15

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.0044. Min Act: -0.0001

Data Index: 1570464 (Python Code)

Max Activating Token Index: 280

Text #16

Max Range: 1.4104. Min Range: -1.4104

Max Act: 0.9729. Min Act: -0.0001

Data Index: 1432154 (Python Code)

Max Activating Token Index: 242

Text #17

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.0034. Min Act: -0.0001

Data Index: 1572181 (Python Code)

Max Activating Token Index: 277

Text #18

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.0033. Min Act: -0.0001

Data Index: 1383697 (Python Code)

Max Activating Token Index: 202

Text #19

Max Range: 1.4104. Min Range: -1.4104

Max Act: 0.9973. Min Act: -0.0001

Data Index: 1418392 (Python Code)

Max Activating Token Index: 29