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

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

Neuron 1057 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: 1.8283. Min Range: -1.8283

Max Act: 1.8283. Min Act: -0.0000

Data Index: 1593919 (Python Code)

Max Activating Token Index: 256

Text #1

Max Range: 1.8283. Min Range: -1.8283

Max Act: 1.6387. Min Act: -0.0000

Data Index: 1381258 (Python Code)

Max Activating Token Index: 844

Text #2

Max Range: 1.8283. Min Range: -1.8283

Max Act: 1.4143. Min Act: -0.0000

Data Index: 1591644 (Python Code)

Max Activating Token Index: 317

Text #3

Max Range: 1.8283. Min Range: -1.8283

Max Act: 1.4967. Min Act: -0.0000

Data Index: 1606568 (Python Code)

Max Activating Token Index: 228

Text #4

Max Range: 1.8283. Min Range: -1.8283

Max Act: 1.5296. Min Act: -0.0000

Data Index: 1511787 (Python Code)

Max Activating Token Index: 553

Text #5

Max Range: 1.8283. Min Range: -1.8283

Max Act: 1.5991. Min Act: -0.0000

Data Index: 1391992 (Python Code)

Max Activating Token Index: 790

Text #6

Max Range: 1.8283. Min Range: -1.8283

Max Act: 1.3940. Min Act: -0.0000

Data Index: 1579833 (Python Code)

Max Activating Token Index: 67

Text #7

Max Range: 1.8283. Min Range: -1.8283

Max Act: 1.4006. Min Act: -0.0000

Data Index: 1577432 (Python Code)

Max Activating Token Index: 675

Text #8

Max Range: 1.8283. Min Range: -1.8283

Max Act: 1.4295. Min Act: -0.0000

Data Index: 1378238 (Python Code)

Max Activating Token Index: 240

Text #9

Max Range: 1.8283. Min Range: -1.8283

Max Act: 1.4212. Min Act: -0.0000

Data Index: 1441077 (Python Code)

Max Activating Token Index: 532

Text #10

Max Range: 1.8283. Min Range: -1.8283

Max Act: 1.3642. Min Act: -0.0000

Data Index: 1506353 (Python Code)

Max Activating Token Index: 43

Text #11

Max Range: 1.8283. Min Range: -1.8283

Max Act: 1.3614. Min Act: -0.0000

Data Index: 1435344 (Python Code)

Max Activating Token Index: 16

Text #12

Max Range: 1.8283. Min Range: -1.8283

Max Act: 1.3501. Min Act: -0.0000

Data Index: 1448822 (Python Code)

Max Activating Token Index: 89

Text #13

Max Range: 1.8283. Min Range: -1.8283

Max Act: 1.3559. Min Act: -0.0000

Data Index: 1506919 (Python Code)

Max Activating Token Index: 429

Text #14

Max Range: 1.8283. Min Range: -1.8283

Max Act: 1.3158. Min Act: -0.0000

Data Index: 1475164 (Python Code)

Max Activating Token Index: 565

Text #15

Max Range: 1.8283. Min Range: -1.8283

Max Act: 1.3453. Min Act: -0.0000

Data Index: 1477753 (Python Code)

Max Activating Token Index: 30

Text #16

Max Range: 1.8283. Min Range: -1.8283

Max Act: 1.3257. Min Act: -0.0000

Data Index: 1594770 (Python Code)

Max Activating Token Index: 175

Text #17

Max Range: 1.8283. Min Range: -1.8283

Max Act: 1.3656. Min Act: -0.0000

Data Index: 1544166 (Python Code)

Max Activating Token Index: 53

Text #18

Max Range: 1.8283. Min Range: -1.8283

Max Act: 1.3221. Min Act: -0.0000

Data Index: 1466827 (Python Code)

Max Activating Token Index: 831

Text #19

Max Range: 1.8283. Min Range: -1.8283

Max Act: 1.3567. Min Act: -0.0000

Data Index: 1485800 (Python Code)

Max Activating Token Index: 296