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

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

Neuron 1929 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: 4.1837. Min Range: -4.1837

Max Act: 4.1837. Min Act: -0.1700

Data Index: 218777 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 4.1837. Min Range: -4.1837

Max Act: 4.0096. Min Act: -0.1700

Data Index: 4905 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 4.1837. Min Range: -4.1837

Max Act: 4.0053. Min Act: -0.1700

Data Index: 348884 (C4 (Web Text))

Max Activating Token Index: 283

Text #3

Max Range: 4.1837. Min Range: -4.1837

Max Act: 3.9494. Min Act: -0.1700

Data Index: 193334 (C4 (Web Text))

Max Activating Token Index: 244

Text #4

Max Range: 4.1837. Min Range: -4.1837

Max Act: 3.9140. Min Act: -0.1700

Data Index: 1042369 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 4.1837. Min Range: -4.1837

Max Act: 3.9018. Min Act: -0.1700

Data Index: 802748 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 4.1837. Min Range: -4.1837

Max Act: 3.7848. Min Act: -0.1700

Data Index: 1439763 (Python Code)

Max Activating Token Index: 734

Text #7

Max Range: 4.1837. Min Range: -4.1837

Max Act: 3.9018. Min Act: -0.1700

Data Index: 116432 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 4.1837. Min Range: -4.1837

Max Act: 3.8905. Min Act: -0.1700

Data Index: 618157 (C4 (Web Text))

Max Activating Token Index: 430

Text #9

Max Range: 4.1837. Min Range: -4.1837

Max Act: 3.8767. Min Act: -0.1700

Data Index: 60730 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 4.1837. Min Range: -4.1837

Max Act: 3.8345. Min Act: -0.1700

Data Index: 380175 (C4 (Web Text))

Max Activating Token Index: 341

Text #11

Max Range: 4.1837. Min Range: -4.1837

Max Act: 3.8555. Min Act: -0.1700

Data Index: 1639460 (Python Code)

Max Activating Token Index: 964

Text #12

Max Range: 4.1837. Min Range: -4.1837

Max Act: 3.9248. Min Act: -0.1700

Data Index: 1302764 (C4 (Web Text))

Max Activating Token Index: 774

Text #13

Max Range: 4.1837. Min Range: -4.1837

Max Act: 3.8321. Min Act: -0.1700

Data Index: 1551312 (Python Code)

Max Activating Token Index: 632

Text #14

Max Range: 4.1837. Min Range: -4.1837

Max Act: 3.8260. Min Act: -0.1700

Data Index: 1408510 (Python Code)

Max Activating Token Index: 591

Text #15

Max Range: 4.1837. Min Range: -4.1837

Max Act: 3.8611. Min Act: -0.1700

Data Index: 1232860 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 4.1837. Min Range: -4.1837

Max Act: 3.8535. Min Act: -0.1700

Data Index: 216143 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 4.1837. Min Range: -4.1837

Max Act: 3.7909. Min Act: -0.1700

Data Index: 1002973 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 4.1837. Min Range: -4.1837

Max Act: 3.8070. Min Act: -0.1700

Data Index: 995690 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 4.1837. Min Range: -4.1837

Max Act: 3.8310. Min Act: -0.1700

Data Index: 751993 (C4 (Web Text))

Max Activating Token Index: 697