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

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

Neuron 550 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: 3.8240. Min Range: -3.8240

Max Act: 3.8240. Min Act: -0.1111

Data Index: 1444114 (Python Code)

Max Activating Token Index: 261

Text #1

Max Range: 3.8240. Min Range: -3.8240

Max Act: 3.6319. Min Act: -0.1681

Data Index: 1624899 (Python Code)

Max Activating Token Index: 905

Text #2

Max Range: 3.8240. Min Range: -3.8240

Max Act: 3.5139. Min Act: -0.1699

Data Index: 229188 (C4 (Web Text))

Max Activating Token Index: 357

Text #3

Max Range: 3.8240. Min Range: -3.8240

Max Act: 3.5464. Min Act: -0.1660

Data Index: 1535293 (Python Code)

Max Activating Token Index: 1013

Text #4

Max Range: 3.8240. Min Range: -3.8240

Max Act: 3.5169. Min Act: -0.1699

Data Index: 1238793 (C4 (Web Text))

Max Activating Token Index: 184

Text #5

Max Range: 3.8240. Min Range: -3.8240

Max Act: 3.4946. Min Act: -0.1700

Data Index: 1378124 (Python Code)

Max Activating Token Index: 711

Text #6

Max Range: 3.8240. Min Range: -3.8240

Max Act: 3.5095. Min Act: -0.1111

Data Index: 1573995 (Python Code)

Max Activating Token Index: 485

Text #7

Max Range: 3.8240. Min Range: -3.8240

Max Act: 3.4748. Min Act: -0.1695

Data Index: 1655389 (Python Code)

Max Activating Token Index: 331

Text #8

Max Range: 3.8240. Min Range: -3.8240

Max Act: 3.4715. Min Act: -0.1700

Data Index: 379935 (C4 (Web Text))

Max Activating Token Index: 456

Text #9

Max Range: 3.8240. Min Range: -3.8240

Max Act: 3.4619. Min Act: -0.1692

Data Index: 1603888 (Python Code)

Max Activating Token Index: 699

Text #10

Max Range: 3.8240. Min Range: -3.8240

Max Act: 3.4648. Min Act: -0.1608

Data Index: 1408742 (Python Code)

Max Activating Token Index: 704

Text #11

Max Range: 3.8240. Min Range: -3.8240

Max Act: 3.4550. Min Act: -0.1696

Data Index: 803804 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 3.8240. Min Range: -3.8240

Max Act: 3.4576. Min Act: -0.1699

Data Index: 463236 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 3.8240. Min Range: -3.8240

Max Act: 3.4219. Min Act: -0.1698

Data Index: 697465 (C4 (Web Text))

Max Activating Token Index: 657

Text #14

Max Range: 3.8240. Min Range: -3.8240

Max Act: 3.4381. Min Act: -0.1687

Data Index: 1513344 (Python Code)

Max Activating Token Index: 669

Text #15

Max Range: 3.8240. Min Range: -3.8240

Max Act: 3.4357. Min Act: -0.1700

Data Index: 1604847 (Python Code)

Max Activating Token Index: 399

Text #16

Max Range: 3.8240. Min Range: -3.8240

Max Act: 3.4442. Min Act: -0.1700

Data Index: 1580158 (Python Code)

Max Activating Token Index: 186

Text #17

Max Range: 3.8240. Min Range: -3.8240

Max Act: 3.4438. Min Act: -0.1698

Data Index: 1428880 (Python Code)

Max Activating Token Index: 149

Text #18

Max Range: 3.8240. Min Range: -3.8240

Max Act: 3.4165. Min Act: -0.1697

Data Index: 686106 (C4 (Web Text))

Max Activating Token Index: 38

Text #19

Max Range: 3.8240. Min Range: -3.8240

Max Act: 3.4432. Min Act: -0.1696

Data Index: 891726 (C4 (Web Text))

Max Activating Token Index: 841