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

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

Neuron 256 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: 4.2596. Min Range: -4.2596

Max Act: 4.2596. Min Act: -0.1700

Data Index: 902337 (C4 (Web Text))

Max Activating Token Index: 172

Text #1

Max Range: 4.2596. Min Range: -4.2596

Max Act: 4.2374. Min Act: -0.1700

Data Index: 1170922 (C4 (Web Text))

Max Activating Token Index: 670

Text #2

Max Range: 4.2596. Min Range: -4.2596

Max Act: 4.2287. Min Act: -0.1700

Data Index: 81032 (C4 (Web Text))

Max Activating Token Index: 737

Text #3

Max Range: 4.2596. Min Range: -4.2596

Max Act: 4.2202. Min Act: -0.1700

Data Index: 692041 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 4.2596. Min Range: -4.2596

Max Act: 4.2147. Min Act: -0.1700

Data Index: 303645 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 4.2596. Min Range: -4.2596

Max Act: 4.1765. Min Act: -0.1700

Data Index: 893754 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 4.2596. Min Range: -4.2596

Max Act: 4.1776. Min Act: -0.1700

Data Index: 1131742 (C4 (Web Text))

Max Activating Token Index: 352

Text #7

Max Range: 4.2596. Min Range: -4.2596

Max Act: 4.1830. Min Act: -0.1700

Data Index: 655668 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 4.2596. Min Range: -4.2596

Max Act: 4.1581. Min Act: -0.1700

Data Index: 1156265 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 4.2596. Min Range: -4.2596

Max Act: 4.1566. Min Act: -0.1700

Data Index: 644750 (C4 (Web Text))

Max Activating Token Index: 385

Text #10

Max Range: 4.2596. Min Range: -4.2596

Max Act: 4.1652. Min Act: -0.1700

Data Index: 1033002 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 4.2596. Min Range: -4.2596

Max Act: 4.1630. Min Act: -0.1700

Data Index: 506431 (C4 (Web Text))

Max Activating Token Index: 762

Text #12

Max Range: 4.2596. Min Range: -4.2596

Max Act: 4.1383. Min Act: -0.1700

Data Index: 814330 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 4.2596. Min Range: -4.2596

Max Act: 4.1606. Min Act: -0.1700

Data Index: 249133 (C4 (Web Text))

Max Activating Token Index: 347

Text #14

Max Range: 4.2596. Min Range: -4.2596

Max Act: 4.1452. Min Act: -0.1700

Data Index: 402563 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 4.2596. Min Range: -4.2596

Max Act: 4.1525. Min Act: -0.1700

Data Index: 422096 (C4 (Web Text))

Max Activating Token Index: 847

Text #16

Max Range: 4.2596. Min Range: -4.2596

Max Act: 4.1432. Min Act: -0.1700

Data Index: 554602 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 4.2596. Min Range: -4.2596

Max Act: 4.1498. Min Act: -0.1700

Data Index: 857623 (C4 (Web Text))

Max Activating Token Index: 544

Text #18

Max Range: 4.2596. Min Range: -4.2596

Max Act: 4.1441. Min Act: -0.1700

Data Index: 259598 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 4.2596. Min Range: -4.2596

Max Act: 4.1303. Min Act: -0.1700

Data Index: 492995 (C4 (Web Text))

Max Activating Token Index: 335