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

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

Neuron 636 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: 9.2269. Min Range: -9.2269

Max Act: 9.2269. Min Act: -0.1619

Data Index: 420165 (C4 (Web Text))

Max Activating Token Index: 885

Text #1

Max Range: 9.2269. Min Range: -9.2269

Max Act: 9.0943. Min Act: -0.1699

Data Index: 634425 (C4 (Web Text))

Max Activating Token Index: 346

Text #2

Max Range: 9.2269. Min Range: -9.2269

Max Act: 9.0394. Min Act: -0.1394

Data Index: 1126322 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 9.2269. Min Range: -9.2269

Max Act: 8.9773. Min Act: -0.1508

Data Index: 97041 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 9.2269. Min Range: -9.2269

Max Act: 8.9938. Min Act: -0.1561

Data Index: 673770 (C4 (Web Text))

Max Activating Token Index: 652

Text #5

Max Range: 9.2269. Min Range: -9.2269

Max Act: 8.8391. Min Act: -0.1686

Data Index: 698148 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 9.2269. Min Range: -9.2269

Max Act: 8.7329. Min Act: -0.1651

Data Index: 1014021 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 9.2269. Min Range: -9.2269

Max Act: 8.7482. Min Act: -0.1700

Data Index: 1296102 (C4 (Web Text))

Max Activating Token Index: 499

Text #8

Max Range: 9.2269. Min Range: -9.2269

Max Act: 8.7089. Min Act: -0.1320

Data Index: 493035 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 9.2269. Min Range: -9.2269

Max Act: 8.6355. Min Act: -0.1700

Data Index: 1185361 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 9.2269. Min Range: -9.2269

Max Act: 8.6174. Min Act: -0.1700

Data Index: 121382 (C4 (Web Text))

Max Activating Token Index: 482

Text #11

Max Range: 9.2269. Min Range: -9.2269

Max Act: 8.5402. Min Act: -0.1699

Data Index: 1243824 (C4 (Web Text))

Max Activating Token Index: 511

Text #12

Max Range: 9.2269. Min Range: -9.2269

Max Act: 8.5557. Min Act: -0.1700

Data Index: 88564 (C4 (Web Text))

Max Activating Token Index: 420

Text #13

Max Range: 9.2269. Min Range: -9.2269

Max Act: 8.5425. Min Act: -0.1456

Data Index: 205864 (C4 (Web Text))

Max Activating Token Index: 369

Text #14

Max Range: 9.2269. Min Range: -9.2269

Max Act: 8.5359. Min Act: -0.1694

Data Index: 569552 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 9.2269. Min Range: -9.2269

Max Act: 8.5628. Min Act: -0.0226

Data Index: 994031 (C4 (Web Text))

Max Activating Token Index: 486

Text #16

Max Range: 9.2269. Min Range: -9.2269

Max Act: 8.5717. Min Act: -0.1700

Data Index: 399868 (C4 (Web Text))

Max Activating Token Index: 843

Text #17

Max Range: 9.2269. Min Range: -9.2269

Max Act: 8.4512. Min Act: -0.1699

Data Index: 146313 (C4 (Web Text))

Max Activating Token Index: 99

Text #18

Max Range: 9.2269. Min Range: -9.2269

Max Act: 8.4838. Min Act: 0.0060

Data Index: 146778 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 9.2269. Min Range: -9.2269

Max Act: 8.4673. Min Act: -0.1086

Data Index: 1215887 (C4 (Web Text))

Max Activating Token Index: 92