Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1052 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.7620. Min Range: -5.7620

Max Act: 5.7620. Min Act: -0.1700

Data Index: 1623303 (Python Code)

Max Activating Token Index: 662

Text #1

Max Range: 5.7620. Min Range: -5.7620

Max Act: 5.5745. Min Act: -0.1700

Data Index: 422023 (C4 (Web Text))

Max Activating Token Index: 863

Text #2

Max Range: 5.7620. Min Range: -5.7620

Max Act: 5.6057. Min Act: -0.1700

Data Index: 1219764 (C4 (Web Text))

Max Activating Token Index: 454

Text #3

Max Range: 5.7620. Min Range: -5.7620

Max Act: 5.5120. Min Act: -0.1700

Data Index: 182136 (C4 (Web Text))

Max Activating Token Index: 659

Text #4

Max Range: 5.7620. Min Range: -5.7620

Max Act: 5.3870. Min Act: -0.1700

Data Index: 653959 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 5.7620. Min Range: -5.7620

Max Act: 5.4182. Min Act: -0.1700

Data Index: 756227 (C4 (Web Text))

Max Activating Token Index: 591

Text #6

Max Range: 5.7620. Min Range: -5.7620

Max Act: 5.4495. Min Act: -0.1700

Data Index: 1329798 (C4 (Web Text))

Max Activating Token Index: 761

Text #7

Max Range: 5.7620. Min Range: -5.7620

Max Act: 5.4182. Min Act: -0.1700

Data Index: 1339368 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 5.7620. Min Range: -5.7620

Max Act: 5.3870. Min Act: -0.1700

Data Index: 1180491 (C4 (Web Text))

Max Activating Token Index: 378

Text #9

Max Range: 5.7620. Min Range: -5.7620

Max Act: 5.4182. Min Act: -0.1700

Data Index: 1601991 (Python Code)

Max Activating Token Index: 647

Text #10

Max Range: 5.7620. Min Range: -5.7620

Max Act: 5.3870. Min Act: -0.1700

Data Index: 96684 (C4 (Web Text))

Max Activating Token Index: 866

Text #11

Max Range: 5.7620. Min Range: -5.7620

Max Act: 5.4182. Min Act: -0.1700

Data Index: 408993 (C4 (Web Text))

Max Activating Token Index: 109

Text #12

Max Range: 5.7620. Min Range: -5.7620

Max Act: 5.3870. Min Act: -0.1700

Data Index: 899812 (C4 (Web Text))

Max Activating Token Index: 707

Text #13

Max Range: 5.7620. Min Range: -5.7620

Max Act: 5.3870. Min Act: -0.1700

Data Index: 365097 (C4 (Web Text))

Max Activating Token Index: 265

Text #14

Max Range: 5.7620. Min Range: -5.7620

Max Act: 5.4182. Min Act: -0.1700

Data Index: 341866 (C4 (Web Text))

Max Activating Token Index: 619

Text #15

Max Range: 5.7620. Min Range: -5.7620

Max Act: 5.3870. Min Act: -0.1700

Data Index: 76391 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 5.7620. Min Range: -5.7620

Max Act: 5.3870. Min Act: -0.1700

Data Index: 493330 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 5.7620. Min Range: -5.7620

Max Act: 5.3557. Min Act: -0.1700

Data Index: 1030190 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 5.7620. Min Range: -5.7620

Max Act: 5.3870. Min Act: -0.1700

Data Index: 131565 (C4 (Web Text))

Max Activating Token Index: 624

Text #19

Max Range: 5.7620. Min Range: -5.7620

Max Act: 5.3870. Min Act: -0.1700

Data Index: 1565039 (Python Code)

Max Activating Token Index: 868