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

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

Neuron 1581 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: 3.8219. Min Range: -3.8219

Max Act: 3.8088. Min Act: -0.1696

Data Index: 284508 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 3.8219. Min Range: -3.8219

Max Act: 3.8219. Min Act: -0.1700

Data Index: 65903 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 3.8219. Min Range: -3.8219

Max Act: 3.7618. Min Act: -0.1700

Data Index: 1080343 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 3.8219. Min Range: -3.8219

Max Act: 3.7755. Min Act: -0.1700

Data Index: 703186 (C4 (Web Text))

Max Activating Token Index: 902

Text #4

Max Range: 3.8219. Min Range: -3.8219

Max Act: 3.7595. Min Act: -0.1700

Data Index: 222847 (C4 (Web Text))

Max Activating Token Index: 929

Text #5

Max Range: 3.8219. Min Range: -3.8219

Max Act: 3.7803. Min Act: -0.1699

Data Index: 660199 (C4 (Web Text))

Max Activating Token Index: 310

Text #6

Max Range: 3.8219. Min Range: -3.8219

Max Act: 3.7550. Min Act: -0.1699

Data Index: 904583 (C4 (Web Text))

Max Activating Token Index: 664

Text #7

Max Range: 3.8219. Min Range: -3.8219

Max Act: 3.7663. Min Act: -0.1699

Data Index: 1021776 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 3.8219. Min Range: -3.8219

Max Act: 3.7502. Min Act: -0.1697

Data Index: 745864 (C4 (Web Text))

Max Activating Token Index: 474

Text #9

Max Range: 3.8219. Min Range: -3.8219

Max Act: 3.7327. Min Act: -0.1699

Data Index: 74264 (C4 (Web Text))

Max Activating Token Index: 712

Text #10

Max Range: 3.8219. Min Range: -3.8219

Max Act: 3.7450. Min Act: -0.1694

Data Index: 771801 (C4 (Web Text))

Max Activating Token Index: 795

Text #11

Max Range: 3.8219. Min Range: -3.8219

Max Act: 3.7373. Min Act: -0.1693

Data Index: 573595 (C4 (Web Text))

Max Activating Token Index: 630

Text #12

Max Range: 3.8219. Min Range: -3.8219

Max Act: 3.7282. Min Act: -0.1691

Data Index: 877077 (C4 (Web Text))

Max Activating Token Index: 709

Text #13

Max Range: 3.8219. Min Range: -3.8219

Max Act: 3.7141. Min Act: -0.1647

Data Index: 407381 (C4 (Web Text))

Max Activating Token Index: 364

Text #14

Max Range: 3.8219. Min Range: -3.8219

Max Act: 3.7493. Min Act: -0.1700

Data Index: 947605 (C4 (Web Text))

Max Activating Token Index: 118

Text #15

Max Range: 3.8219. Min Range: -3.8219

Max Act: 3.7409. Min Act: -0.1700

Data Index: 283908 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 3.8219. Min Range: -3.8219

Max Act: 3.7180. Min Act: -0.1698

Data Index: 277176 (C4 (Web Text))

Max Activating Token Index: 1007

Text #17

Max Range: 3.8219. Min Range: -3.8219

Max Act: 3.6965. Min Act: -0.1688

Data Index: 673814 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 3.8219. Min Range: -3.8219

Max Act: 3.6997. Min Act: -0.1695

Data Index: 269526 (C4 (Web Text))

Max Activating Token Index: 412

Text #19

Max Range: 3.8219. Min Range: -3.8219

Max Act: 3.6925. Min Act: -0.1700

Data Index: 641514 (C4 (Web Text))

Max Activating Token Index: 389