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

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

Neuron 1941 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: 3.3623. Min Range: -3.3623

Max Act: 3.3623. Min Act: -0.1700

Data Index: 56913 (C4 (Web Text))

Max Activating Token Index: 981

Text #1

Max Range: 3.3623. Min Range: -3.3623

Max Act: 3.2971. Min Act: -0.1699

Data Index: 1102997 (C4 (Web Text))

Max Activating Token Index: 286

Text #2

Max Range: 3.3623. Min Range: -3.3623

Max Act: 3.2041. Min Act: -0.1700

Data Index: 782898 (C4 (Web Text))

Max Activating Token Index: 226

Text #3

Max Range: 3.3623. Min Range: -3.3623

Max Act: 3.2086. Min Act: -0.1700

Data Index: 828383 (C4 (Web Text))

Max Activating Token Index: 929

Text #4

Max Range: 3.3623. Min Range: -3.3623

Max Act: 3.2017. Min Act: -0.1700

Data Index: 300081 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 3.3623. Min Range: -3.3623

Max Act: 3.2008. Min Act: -0.1698

Data Index: 237261 (C4 (Web Text))

Max Activating Token Index: 295

Text #6

Max Range: 3.3623. Min Range: -3.3623

Max Act: 3.2006. Min Act: -0.1699

Data Index: 1125755 (C4 (Web Text))

Max Activating Token Index: 312

Text #7

Max Range: 3.3623. Min Range: -3.3623

Max Act: 3.1726. Min Act: -0.1700

Data Index: 1198107 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 3.3623. Min Range: -3.3623

Max Act: 3.1604. Min Act: -0.1700

Data Index: 129681 (C4 (Web Text))

Max Activating Token Index: 559

Text #9

Max Range: 3.3623. Min Range: -3.3623

Max Act: 3.1748. Min Act: -0.1673

Data Index: 59882 (C4 (Web Text))

Max Activating Token Index: 700

Text #10

Max Range: 3.3623. Min Range: -3.3623

Max Act: 3.1766. Min Act: -0.1700

Data Index: 943098 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 3.3623. Min Range: -3.3623

Max Act: 3.1863. Min Act: -0.1697

Data Index: 246612 (C4 (Web Text))

Max Activating Token Index: 887

Text #12

Max Range: 3.3623. Min Range: -3.3623

Max Act: 3.1846. Min Act: -0.1699

Data Index: 793025 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 3.3623. Min Range: -3.3623

Max Act: 3.1805. Min Act: -0.1700

Data Index: 1304299 (C4 (Web Text))

Max Activating Token Index: 119

Text #14

Max Range: 3.3623. Min Range: -3.3623

Max Act: 3.1589. Min Act: -0.1680

Data Index: 585325 (C4 (Web Text))

Max Activating Token Index: 909

Text #15

Max Range: 3.3623. Min Range: -3.3623

Max Act: 3.1353. Min Act: -0.1700

Data Index: 337591 (C4 (Web Text))

Max Activating Token Index: 334

Text #16

Max Range: 3.3623. Min Range: -3.3623

Max Act: 3.1559. Min Act: -0.1639

Data Index: 679931 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 3.3623. Min Range: -3.3623

Max Act: 3.1488. Min Act: -0.1699

Data Index: 431695 (C4 (Web Text))

Max Activating Token Index: 620

Text #18

Max Range: 3.3623. Min Range: -3.3623

Max Act: 3.1434. Min Act: -0.1700

Data Index: 1045676 (C4 (Web Text))

Max Activating Token Index: 624

Text #19

Max Range: 3.3623. Min Range: -3.3623

Max Act: 3.1436. Min Act: -0.1699

Data Index: 481408 (C4 (Web Text))

Max Activating Token Index: 973