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

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

Neuron 1694 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: 3.2819. Min Range: -3.2819

Max Act: 3.2754. Min Act: -0.1693

Data Index: 1110294 (C4 (Web Text))

Max Activating Token Index: 753

Text #1

Max Range: 3.2819. Min Range: -3.2819

Max Act: 3.2819. Min Act: -0.1440

Data Index: 133231 (C4 (Web Text))

Max Activating Token Index: 446

Text #2

Max Range: 3.2819. Min Range: -3.2819

Max Act: 3.2615. Min Act: -0.1586

Data Index: 1277931 (C4 (Web Text))

Max Activating Token Index: 921

Text #3

Max Range: 3.2819. Min Range: -3.2819

Max Act: 3.2398. Min Act: -0.1389

Data Index: 80276 (C4 (Web Text))

Max Activating Token Index: 361

Text #4

Max Range: 3.2819. Min Range: -3.2819

Max Act: 3.2420. Min Act: -0.1696

Data Index: 781679 (C4 (Web Text))

Max Activating Token Index: 380

Text #5

Max Range: 3.2819. Min Range: -3.2819

Max Act: 3.2213. Min Act: -0.1577

Data Index: 447102 (C4 (Web Text))

Max Activating Token Index: 295

Text #6

Max Range: 3.2819. Min Range: -3.2819

Max Act: 3.1920. Min Act: -0.1700

Data Index: 1126552 (C4 (Web Text))

Max Activating Token Index: 410

Text #7

Max Range: 3.2819. Min Range: -3.2819

Max Act: 3.1889. Min Act: -0.1542

Data Index: 445205 (C4 (Web Text))

Max Activating Token Index: 651

Text #8

Max Range: 3.2819. Min Range: -3.2819

Max Act: 3.1841. Min Act: -0.1639

Data Index: 1265692 (C4 (Web Text))

Max Activating Token Index: 426

Text #9

Max Range: 3.2819. Min Range: -3.2819

Max Act: 3.1823. Min Act: -0.1700

Data Index: 1309105 (C4 (Web Text))

Max Activating Token Index: 670

Text #10

Max Range: 3.2819. Min Range: -3.2819

Max Act: 3.1892. Min Act: -0.1692

Data Index: 317183 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 3.2819. Min Range: -3.2819

Max Act: 3.1781. Min Act: -0.1685

Data Index: 200127 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 3.2819. Min Range: -3.2819

Max Act: 3.1683. Min Act: -0.1700

Data Index: 8571 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 3.2819. Min Range: -3.2819

Max Act: 3.1746. Min Act: -0.1687

Data Index: 1128398 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 3.2819. Min Range: -3.2819

Max Act: 3.1434. Min Act: -0.1606

Data Index: 833720 (C4 (Web Text))

Max Activating Token Index: 939

Text #15

Max Range: 3.2819. Min Range: -3.2819

Max Act: 3.1423. Min Act: -0.1640

Data Index: 761924 (C4 (Web Text))

Max Activating Token Index: 127

Text #16

Max Range: 3.2819. Min Range: -3.2819

Max Act: 3.1400. Min Act: -0.1389

Data Index: 15066 (C4 (Web Text))

Max Activating Token Index: 194

Text #17

Max Range: 3.2819. Min Range: -3.2819

Max Act: 3.1113. Min Act: -0.1550

Data Index: 1021029 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 3.2819. Min Range: -3.2819

Max Act: 3.1188. Min Act: -0.1694

Data Index: 211820 (C4 (Web Text))

Max Activating Token Index: 568

Text #19

Max Range: 3.2819. Min Range: -3.2819

Max Act: 3.1167. Min Act: -0.1389

Data Index: 225185 (C4 (Web Text))

Max Activating Token Index: 436