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

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

Neuron 555 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: 4.4354. Min Range: -4.4354

Max Act: 4.4235. Min Act: -0.1698

Data Index: 427222 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 4.4354. Min Range: -4.4354

Max Act: 4.4354. Min Act: -0.1700

Data Index: 397140 (C4 (Web Text))

Max Activating Token Index: 547

Text #2

Max Range: 4.4354. Min Range: -4.4354

Max Act: 4.2771. Min Act: -0.1700

Data Index: 1094543 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 4.4354. Min Range: -4.4354

Max Act: 4.2432. Min Act: -0.1699

Data Index: 1390854 (Python Code)

Max Activating Token Index: 727

Text #4

Max Range: 4.4354. Min Range: -4.4354

Max Act: 4.2005. Min Act: -0.1640

Data Index: 749491 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 4.4354. Min Range: -4.4354

Max Act: 4.1586. Min Act: -0.1700

Data Index: 611381 (C4 (Web Text))

Max Activating Token Index: 211

Text #6

Max Range: 4.4354. Min Range: -4.4354

Max Act: 4.1658. Min Act: -0.1700

Data Index: 131361 (C4 (Web Text))

Max Activating Token Index: 250

Text #7

Max Range: 4.4354. Min Range: -4.4354

Max Act: 4.1689. Min Act: -0.1700

Data Index: 1301529 (C4 (Web Text))

Max Activating Token Index: 280

Text #8

Max Range: 4.4354. Min Range: -4.4354

Max Act: 4.1783. Min Act: -0.1687

Data Index: 356748 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 4.4354. Min Range: -4.4354

Max Act: 4.1435. Min Act: -0.1639

Data Index: 309777 (C4 (Web Text))

Max Activating Token Index: 244

Text #10

Max Range: 4.4354. Min Range: -4.4354

Max Act: 4.1359. Min Act: -0.1699

Data Index: 463475 (C4 (Web Text))

Max Activating Token Index: 816

Text #11

Max Range: 4.4354. Min Range: -4.4354

Max Act: 4.1059. Min Act: -0.1698

Data Index: 968194 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 4.4354. Min Range: -4.4354

Max Act: 4.0924. Min Act: -0.1700

Data Index: 16626 (C4 (Web Text))

Max Activating Token Index: 381

Text #13

Max Range: 4.4354. Min Range: -4.4354

Max Act: 4.1008. Min Act: -0.1674

Data Index: 475151 (C4 (Web Text))

Max Activating Token Index: 986

Text #14

Max Range: 4.4354. Min Range: -4.4354

Max Act: 4.0899. Min Act: -0.1700

Data Index: 1463280 (Python Code)

Max Activating Token Index: 787

Text #15

Max Range: 4.4354. Min Range: -4.4354

Max Act: 4.0901. Min Act: -0.1699

Data Index: 1547839 (Python Code)

Max Activating Token Index: 660

Text #16

Max Range: 4.4354. Min Range: -4.4354

Max Act: 4.0505. Min Act: -0.1351

Data Index: 387482 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 4.4354. Min Range: -4.4354

Max Act: 4.0335. Min Act: -0.1697

Data Index: 1354718 (C4 (Web Text))

Max Activating Token Index: 443

Text #18

Max Range: 4.4354. Min Range: -4.4354

Max Act: 4.0579. Min Act: -0.1699

Data Index: 359077 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 4.4354. Min Range: -4.4354

Max Act: 4.0552. Min Act: -0.1697

Data Index: 1231949 (C4 (Web Text))

Max Activating Token Index: 566