Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1328 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.8715. Min Range: -5.8715

Max Act: 5.8402. Min Act: -0.1700

Data Index: 418686 (C4 (Web Text))

Max Activating Token Index: 416

Text #1

Max Range: 5.8715. Min Range: -5.8715

Max Act: 5.8715. Min Act: -0.1700

Data Index: 189006 (C4 (Web Text))

Max Activating Token Index: 1020

Text #2

Max Range: 5.8715. Min Range: -5.8715

Max Act: 5.8090. Min Act: -0.1700

Data Index: 827467 (C4 (Web Text))

Max Activating Token Index: 593

Text #3

Max Range: 5.8715. Min Range: -5.8715

Max Act: 5.7465. Min Act: -0.1700

Data Index: 83745 (C4 (Web Text))

Max Activating Token Index: 461

Text #4

Max Range: 5.8715. Min Range: -5.8715

Max Act: 5.8090. Min Act: -0.1700

Data Index: 841248 (C4 (Web Text))

Max Activating Token Index: 549

Text #5

Max Range: 5.8715. Min Range: -5.8715

Max Act: 5.7152. Min Act: -0.1700

Data Index: 1043220 (C4 (Web Text))

Max Activating Token Index: 509

Text #6

Max Range: 5.8715. Min Range: -5.8715

Max Act: 5.7465. Min Act: -0.1700

Data Index: 48823 (C4 (Web Text))

Max Activating Token Index: 563

Text #7

Max Range: 5.8715. Min Range: -5.8715

Max Act: 5.7777. Min Act: -0.1700

Data Index: 170430 (C4 (Web Text))

Max Activating Token Index: 553

Text #8

Max Range: 5.8715. Min Range: -5.8715

Max Act: 5.7152. Min Act: -0.1700

Data Index: 860594 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 5.8715. Min Range: -5.8715

Max Act: 5.7465. Min Act: -0.1700

Data Index: 1092424 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 5.8715. Min Range: -5.8715

Max Act: 5.6840. Min Act: -0.1700

Data Index: 727071 (C4 (Web Text))

Max Activating Token Index: 171

Text #11

Max Range: 5.8715. Min Range: -5.8715

Max Act: 5.6527. Min Act: -0.1700

Data Index: 752013 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 5.8715. Min Range: -5.8715

Max Act: 5.7465. Min Act: -0.1700

Data Index: 312379 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 5.8715. Min Range: -5.8715

Max Act: 5.6527. Min Act: -0.1700

Data Index: 476333 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 5.8715. Min Range: -5.8715

Max Act: 5.6527. Min Act: -0.1700

Data Index: 968656 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 5.8715. Min Range: -5.8715

Max Act: 5.6840. Min Act: -0.1700

Data Index: 172908 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 5.8715. Min Range: -5.8715

Max Act: 5.7465. Min Act: -0.1700

Data Index: 504869 (C4 (Web Text))

Max Activating Token Index: 198

Text #17

Max Range: 5.8715. Min Range: -5.8715

Max Act: 5.5902. Min Act: -0.1700

Data Index: 863803 (C4 (Web Text))

Max Activating Token Index: 704

Text #18

Max Range: 5.8715. Min Range: -5.8715

Max Act: 5.6215. Min Act: -0.1700

Data Index: 937948 (C4 (Web Text))

Max Activating Token Index: 621

Text #19

Max Range: 5.8715. Min Range: -5.8715

Max Act: 5.6527. Min Act: -0.1700

Data Index: 653328 (C4 (Web Text))

Max Activating Token Index: 16