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

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

Neuron 957 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1668. Min Range: -3.1668

Max Act: 3.1668. Min Act: -0.1700

Data Index: 665792 (C4 (Web Text))

Max Activating Token Index: 405

Text #1

Max Range: 3.1668. Min Range: -3.1668

Max Act: 3.1353. Min Act: -0.1700

Data Index: 915597 (C4 (Web Text))

Max Activating Token Index: 983

Text #2

Max Range: 3.1668. Min Range: -3.1668

Max Act: 3.1196. Min Act: -0.1700

Data Index: 355794 (C4 (Web Text))

Max Activating Token Index: 585

Text #3

Max Range: 3.1668. Min Range: -3.1668

Max Act: 3.1038. Min Act: -0.1700

Data Index: 530449 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 3.1668. Min Range: -3.1668

Max Act: 3.1038. Min Act: -0.1700

Data Index: 860647 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 3.1668. Min Range: -3.1668

Max Act: 3.1196. Min Act: -0.1700

Data Index: 1134971 (C4 (Web Text))

Max Activating Token Index: 891

Text #6

Max Range: 3.1668. Min Range: -3.1668

Max Act: 3.1038. Min Act: -0.1700

Data Index: 463797 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 3.1668. Min Range: -3.1668

Max Act: 3.0880. Min Act: -0.1700

Data Index: 214047 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 3.1668. Min Range: -3.1668

Max Act: 3.1038. Min Act: -0.1700

Data Index: 451875 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 3.1668. Min Range: -3.1668

Max Act: 3.0723. Min Act: -0.1700

Data Index: 485894 (C4 (Web Text))

Max Activating Token Index: 343

Text #10

Max Range: 3.1668. Min Range: -3.1668

Max Act: 3.0723. Min Act: -0.1700

Data Index: 145424 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 3.1668. Min Range: -3.1668

Max Act: 3.0880. Min Act: -0.1700

Data Index: 847575 (C4 (Web Text))

Max Activating Token Index: 295

Text #12

Max Range: 3.1668. Min Range: -3.1668

Max Act: 3.0880. Min Act: -0.1700

Data Index: 532183 (C4 (Web Text))

Max Activating Token Index: 595

Text #13

Max Range: 3.1668. Min Range: -3.1668

Max Act: 3.0880. Min Act: -0.1700

Data Index: 455082 (C4 (Web Text))

Max Activating Token Index: 153

Text #14

Max Range: 3.1668. Min Range: -3.1668

Max Act: 3.0723. Min Act: -0.1700

Data Index: 214432 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 3.1668. Min Range: -3.1668

Max Act: 3.0565. Min Act: -0.1700

Data Index: 112642 (C4 (Web Text))

Max Activating Token Index: 289

Text #16

Max Range: 3.1668. Min Range: -3.1668

Max Act: 3.0723. Min Act: -0.1700

Data Index: 1182327 (C4 (Web Text))

Max Activating Token Index: 316

Text #17

Max Range: 3.1668. Min Range: -3.1668

Max Act: 3.0723. Min Act: -0.1700

Data Index: 586699 (C4 (Web Text))

Max Activating Token Index: 817

Text #18

Max Range: 3.1668. Min Range: -3.1668

Max Act: 3.0565. Min Act: -0.1700

Data Index: 416603 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 3.1668. Min Range: -3.1668

Max Act: 3.0565. Min Act: -0.1700

Data Index: 508857 (C4 (Web Text))

Max Activating Token Index: 849