Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1154 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.9569. Min Range: -3.9569

Max Act: 3.9569. Min Act: -0.1700

Data Index: 1535330 (Python Code)

Max Activating Token Index: 670

Text #1

Max Range: 3.9569. Min Range: -3.9569

Max Act: 3.9135. Min Act: -0.1700

Data Index: 1605559 (Python Code)

Max Activating Token Index: 788

Text #2

Max Range: 3.9569. Min Range: -3.9569

Max Act: 3.9164. Min Act: -0.1700

Data Index: 1434829 (Python Code)

Max Activating Token Index: 183

Text #3

Max Range: 3.9569. Min Range: -3.9569

Max Act: 3.9440. Min Act: -0.1700

Data Index: 1537392 (Python Code)

Max Activating Token Index: 119

Text #4

Max Range: 3.9569. Min Range: -3.9569

Max Act: 3.9121. Min Act: -0.1700

Data Index: 1635487 (Python Code)

Max Activating Token Index: 182

Text #5

Max Range: 3.9569. Min Range: -3.9569

Max Act: 3.8731. Min Act: -0.1700

Data Index: 1555642 (Python Code)

Max Activating Token Index: 742

Text #6

Max Range: 3.9569. Min Range: -3.9569

Max Act: 3.8822. Min Act: -0.1700

Data Index: 1412172 (Python Code)

Max Activating Token Index: 768

Text #7

Max Range: 3.9569. Min Range: -3.9569

Max Act: 3.8967. Min Act: -0.1700

Data Index: 1378049 (Python Code)

Max Activating Token Index: 334

Text #8

Max Range: 3.9569. Min Range: -3.9569

Max Act: 3.8776. Min Act: -0.1700

Data Index: 1410393 (Python Code)

Max Activating Token Index: 893

Text #9

Max Range: 3.9569. Min Range: -3.9569

Max Act: 3.8584. Min Act: -0.1700

Data Index: 1603741 (Python Code)

Max Activating Token Index: 490

Text #10

Max Range: 3.9569. Min Range: -3.9569

Max Act: 3.8562. Min Act: -0.1700

Data Index: 1542375 (Python Code)

Max Activating Token Index: 243

Text #11

Max Range: 3.9569. Min Range: -3.9569

Max Act: 3.8440. Min Act: -0.1700

Data Index: 1524837 (Python Code)

Max Activating Token Index: 466

Text #12

Max Range: 3.9569. Min Range: -3.9569

Max Act: 3.8625. Min Act: -0.1700

Data Index: 1655747 (Python Code)

Max Activating Token Index: 398

Text #13

Max Range: 3.9569. Min Range: -3.9569

Max Act: 3.8477. Min Act: -0.1700

Data Index: 1430194 (Python Code)

Max Activating Token Index: 476

Text #14

Max Range: 3.9569. Min Range: -3.9569

Max Act: 3.8282. Min Act: -0.1700

Data Index: 1387272 (Python Code)

Max Activating Token Index: 970

Text #15

Max Range: 3.9569. Min Range: -3.9569

Max Act: 3.8533. Min Act: -0.1700

Data Index: 1563114 (Python Code)

Max Activating Token Index: 155

Text #16

Max Range: 3.9569. Min Range: -3.9569

Max Act: 3.8396. Min Act: -0.1700

Data Index: 1620798 (Python Code)

Max Activating Token Index: 458

Text #17

Max Range: 3.9569. Min Range: -3.9569

Max Act: 3.8873. Min Act: -0.1700

Data Index: 1367913 (Python Code)

Max Activating Token Index: 1022

Text #18

Max Range: 3.9569. Min Range: -3.9569

Max Act: 3.8467. Min Act: -0.1700

Data Index: 1490407 (Python Code)

Max Activating Token Index: 753

Text #19

Max Range: 3.9569. Min Range: -3.9569

Max Act: 3.8076. Min Act: -0.1700

Data Index: 1417211 (Python Code)

Max Activating Token Index: 224