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

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

Neuron 1944 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: 3.3287. Min Range: -3.3287

Max Act: 3.3287. Min Act: -0.1700

Data Index: 1371515 (Python Code)

Max Activating Token Index: 957

Text #1

Max Range: 3.3287. Min Range: -3.3287

Max Act: 3.2196. Min Act: -0.1700

Data Index: 1401973 (Python Code)

Max Activating Token Index: 749

Text #2

Max Range: 3.3287. Min Range: -3.3287

Max Act: 3.1997. Min Act: -0.1696

Data Index: 590902 (C4 (Web Text))

Max Activating Token Index: 441

Text #3

Max Range: 3.3287. Min Range: -3.3287

Max Act: 3.1633. Min Act: -0.1699

Data Index: 1364348 (Python Code)

Max Activating Token Index: 537

Text #4

Max Range: 3.3287. Min Range: -3.3287

Max Act: 3.0994. Min Act: -0.1700

Data Index: 1438867 (Python Code)

Max Activating Token Index: 249

Text #5

Max Range: 3.3287. Min Range: -3.3287

Max Act: 3.0611. Min Act: -0.1683

Data Index: 122866 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 3.3287. Min Range: -3.3287

Max Act: 3.0511. Min Act: -0.1697

Data Index: 420427 (C4 (Web Text))

Max Activating Token Index: 880

Text #7

Max Range: 3.3287. Min Range: -3.3287

Max Act: 3.0173. Min Act: -0.1700

Data Index: 1617425 (Python Code)

Max Activating Token Index: 205

Text #8

Max Range: 3.3287. Min Range: -3.3287

Max Act: 3.0019. Min Act: -0.1700

Data Index: 1622560 (Python Code)

Max Activating Token Index: 161

Text #9

Max Range: 3.3287. Min Range: -3.3287

Max Act: 2.9972. Min Act: -0.1699

Data Index: 1464494 (Python Code)

Max Activating Token Index: 507

Text #10

Max Range: 3.3287. Min Range: -3.3287

Max Act: 2.9844. Min Act: -0.1700

Data Index: 1534110 (Python Code)

Max Activating Token Index: 640

Text #11

Max Range: 3.3287. Min Range: -3.3287

Max Act: 2.9542. Min Act: -0.1700

Data Index: 1374475 (Python Code)

Max Activating Token Index: 894

Text #12

Max Range: 3.3287. Min Range: -3.3287

Max Act: 2.9677. Min Act: -0.1700

Data Index: 1394832 (Python Code)

Max Activating Token Index: 47

Text #13

Max Range: 3.3287. Min Range: -3.3287

Max Act: 2.9650. Min Act: -0.1695

Data Index: 1473316 (Python Code)

Max Activating Token Index: 587

Text #14

Max Range: 3.3287. Min Range: -3.3287

Max Act: 2.9511. Min Act: -0.1700

Data Index: 485306 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 3.3287. Min Range: -3.3287

Max Act: 2.9623. Min Act: -0.1699

Data Index: 1501667 (Python Code)

Max Activating Token Index: 913

Text #16

Max Range: 3.3287. Min Range: -3.3287

Max Act: 2.9567. Min Act: -0.1700

Data Index: 1492280 (Python Code)

Max Activating Token Index: 979

Text #17

Max Range: 3.3287. Min Range: -3.3287

Max Act: 2.9345. Min Act: -0.1652

Data Index: 1404780 (Python Code)

Max Activating Token Index: 51

Text #18

Max Range: 3.3287. Min Range: -3.3287

Max Act: 2.9351. Min Act: -0.1700

Data Index: 1656776 (Python Code)

Max Activating Token Index: 199

Text #19

Max Range: 3.3287. Min Range: -3.3287

Max Act: 2.9353. Min Act: -0.1700

Data Index: 329011 (C4 (Web Text))

Max Activating Token Index: 50