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

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

Neuron 2354 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5373. Min Range: -4.5373

Max Act: 3.5300. Min Act: -0.0001

Data Index: 1539954 (Python Code)

Max Activating Token Index: 93

Text #1

Max Range: 4.5373. Min Range: -4.5373

Max Act: 4.5373. Min Act: -0.0001

Data Index: 1615257 (Python Code)

Max Activating Token Index: 188

Text #2

Max Range: 4.5373. Min Range: -4.5373

Max Act: 3.1397. Min Act: -0.0000

Data Index: 1406106 (Python Code)

Max Activating Token Index: 60

Text #3

Max Range: 4.5373. Min Range: -4.5373

Max Act: 2.8926. Min Act: -0.0000

Data Index: 1420192 (Python Code)

Max Activating Token Index: 67

Text #4

Max Range: 4.5373. Min Range: -4.5373

Max Act: 2.6085. Min Act: -0.0001

Data Index: 1537593 (Python Code)

Max Activating Token Index: 633

Text #5

Max Range: 4.5373. Min Range: -4.5373

Max Act: 2.8670. Min Act: -0.0000

Data Index: 1656264 (Python Code)

Max Activating Token Index: 92

Text #6

Max Range: 4.5373. Min Range: -4.5373

Max Act: 2.3865. Min Act: -0.0001

Data Index: 1398179 (Python Code)

Max Activating Token Index: 143

Text #7

Max Range: 4.5373. Min Range: -4.5373

Max Act: 2.4917. Min Act: -0.0001

Data Index: 1491166 (Python Code)

Max Activating Token Index: 223

Text #8

Max Range: 4.5373. Min Range: -4.5373

Max Act: 2.6894. Min Act: -0.0000

Data Index: 1374313 (Python Code)

Max Activating Token Index: 552

Text #9

Max Range: 4.5373. Min Range: -4.5373

Max Act: 1.8722. Min Act: -0.0000

Data Index: 1417360 (Python Code)

Max Activating Token Index: 288

Text #10

Max Range: 4.5373. Min Range: -4.5373

Max Act: 2.8147. Min Act: -0.0000

Data Index: 1553372 (Python Code)

Max Activating Token Index: 650

Text #11

Max Range: 4.5373. Min Range: -4.5373

Max Act: 2.4371. Min Act: -0.0000

Data Index: 1368798 (Python Code)

Max Activating Token Index: 190

Text #12

Max Range: 4.5373. Min Range: -4.5373

Max Act: 1.9323. Min Act: -0.0000

Data Index: 1429194 (Python Code)

Max Activating Token Index: 171

Text #13

Max Range: 4.5373. Min Range: -4.5373

Max Act: 2.7076. Min Act: -0.0001

Data Index: 1415172 (Python Code)

Max Activating Token Index: 168

Text #14

Max Range: 4.5373. Min Range: -4.5373

Max Act: 2.5728. Min Act: -0.0001

Data Index: 1438272 (Python Code)

Max Activating Token Index: 459

Text #15

Max Range: 4.5373. Min Range: -4.5373

Max Act: 2.2883. Min Act: -0.0000

Data Index: 1637571 (Python Code)

Max Activating Token Index: 700

Text #16

Max Range: 4.5373. Min Range: -4.5373

Max Act: 2.2893. Min Act: -0.0000

Data Index: 1360734 (Python Code)

Max Activating Token Index: 288

Text #17

Max Range: 4.5373. Min Range: -4.5373

Max Act: 2.2796. Min Act: -0.0001

Data Index: 1410442 (Python Code)

Max Activating Token Index: 26

Text #18

Max Range: 4.5373. Min Range: -4.5373

Max Act: 2.5145. Min Act: -0.0001

Data Index: 1557605 (Python Code)

Max Activating Token Index: 303

Text #19

Max Range: 4.5373. Min Range: -4.5373

Max Act: 2.1538. Min Act: -0.0000

Data Index: 1643897 (Python Code)

Max Activating Token Index: 433