Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 775 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.8615. Min Range: -3.8615

Max Act: 3.7989. Min Act: -0.1700

Data Index: 385816 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 3.8615. Min Range: -3.8615

Max Act: 3.8302. Min Act: -0.1700

Data Index: 26884 (C4 (Web Text))

Max Activating Token Index: 422

Text #2

Max Range: 3.8615. Min Range: -3.8615

Max Act: 3.8615. Min Act: -0.1700

Data Index: 1172504 (C4 (Web Text))

Max Activating Token Index: 728

Text #3

Max Range: 3.8615. Min Range: -3.8615

Max Act: 3.7676. Min Act: -0.1700

Data Index: 220407 (C4 (Web Text))

Max Activating Token Index: 274

Text #4

Max Range: 3.8615. Min Range: -3.8615

Max Act: 3.7676. Min Act: -0.1700

Data Index: 1138251 (C4 (Web Text))

Max Activating Token Index: 533

Text #5

Max Range: 3.8615. Min Range: -3.8615

Max Act: 3.7676. Min Act: -0.1700

Data Index: 138538 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 3.8615. Min Range: -3.8615

Max Act: 3.6737. Min Act: -0.1700

Data Index: 525963 (C4 (Web Text))

Max Activating Token Index: 809

Text #7

Max Range: 3.8615. Min Range: -3.8615

Max Act: 3.7676. Min Act: -0.1700

Data Index: 1051911 (C4 (Web Text))

Max Activating Token Index: 596

Text #8

Max Range: 3.8615. Min Range: -3.8615

Max Act: 3.7989. Min Act: -0.1700

Data Index: 1329385 (C4 (Web Text))

Max Activating Token Index: 861

Text #9

Max Range: 3.8615. Min Range: -3.8615

Max Act: 3.7050. Min Act: -0.1700

Data Index: 694483 (C4 (Web Text))

Max Activating Token Index: 819

Text #10

Max Range: 3.8615. Min Range: -3.8615

Max Act: 3.7050. Min Act: -0.1700

Data Index: 771980 (C4 (Web Text))

Max Activating Token Index: 485

Text #11

Max Range: 3.8615. Min Range: -3.8615

Max Act: 3.7363. Min Act: -0.1700

Data Index: 703040 (C4 (Web Text))

Max Activating Token Index: 674

Text #12

Max Range: 3.8615. Min Range: -3.8615

Max Act: 3.6737. Min Act: -0.1700

Data Index: 819558 (C4 (Web Text))

Max Activating Token Index: 1009

Text #13

Max Range: 3.8615. Min Range: -3.8615

Max Act: 3.6737. Min Act: -0.1700

Data Index: 721712 (C4 (Web Text))

Max Activating Token Index: 281

Text #14

Max Range: 3.8615. Min Range: -3.8615

Max Act: 3.6737. Min Act: -0.1700

Data Index: 231539 (C4 (Web Text))

Max Activating Token Index: 442

Text #15

Max Range: 3.8615. Min Range: -3.8615

Max Act: 3.6737. Min Act: -0.1700

Data Index: 379986 (C4 (Web Text))

Max Activating Token Index: 437

Text #16

Max Range: 3.8615. Min Range: -3.8615

Max Act: 3.6424. Min Act: -0.1700

Data Index: 148348 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 3.8615. Min Range: -3.8615

Max Act: 3.6111. Min Act: -0.1700

Data Index: 533954 (C4 (Web Text))

Max Activating Token Index: 591

Text #18

Max Range: 3.8615. Min Range: -3.8615

Max Act: 3.7050. Min Act: -0.1700

Data Index: 1200730 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 3.8615. Min Range: -3.8615

Max Act: 3.6737. Min Act: -0.1700

Data Index: 226507 (C4 (Web Text))

Max Activating Token Index: 564