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

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

Neuron 530 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: 3.9883. Min Range: -3.9883

Max Act: 3.9883. Min Act: -0.1699

Data Index: 657334 (C4 (Web Text))

Max Activating Token Index: 725

Text #1

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.9390. Min Act: -0.1546

Data Index: 348286 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.9199. Min Act: -0.1700

Data Index: 765160 (C4 (Web Text))

Max Activating Token Index: 775

Text #3

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.9004. Min Act: -0.1689

Data Index: 1141582 (C4 (Web Text))

Max Activating Token Index: 134

Text #4

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.9149. Min Act: -0.1698

Data Index: 86688 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.8987. Min Act: -0.1700

Data Index: 972660 (C4 (Web Text))

Max Activating Token Index: 550

Text #6

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.8582. Min Act: -0.1546

Data Index: 761924 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.8507. Min Act: -0.1622

Data Index: 555457 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.8531. Min Act: -0.1700

Data Index: 802897 (C4 (Web Text))

Max Activating Token Index: 477

Text #9

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.8120. Min Act: -0.1700

Data Index: 685416 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.8230. Min Act: -0.1700

Data Index: 289590 (C4 (Web Text))

Max Activating Token Index: 274

Text #11

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.8004. Min Act: -0.1693

Data Index: 768688 (C4 (Web Text))

Max Activating Token Index: 655

Text #12

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.8033. Min Act: -0.1696

Data Index: 316335 (C4 (Web Text))

Max Activating Token Index: 643

Text #13

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.7789. Min Act: -0.1699

Data Index: 1025959 (C4 (Web Text))

Max Activating Token Index: 655

Text #14

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.7682. Min Act: -0.1678

Data Index: 80276 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.7499. Min Act: -0.1700

Data Index: 200388 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.7339. Min Act: -0.1700

Data Index: 621885 (C4 (Web Text))

Max Activating Token Index: 222

Text #17

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.7262. Min Act: -0.1700

Data Index: 1094314 (C4 (Web Text))

Max Activating Token Index: 171

Text #18

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.7084. Min Act: -0.1650

Data Index: 873319 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.6819. Min Act: -0.1700

Data Index: 251925 (C4 (Web Text))

Max Activating Token Index: 128