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

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

Neuron 544 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2562. Min Range: -5.2562

Max Act: 5.2562. Min Act: -0.1700

Data Index: 279897 (C4 (Web Text))

Max Activating Token Index: 898

Text #1

Max Range: 5.2562. Min Range: -5.2562

Max Act: 5.1625. Min Act: -0.1700

Data Index: 987289 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 5.2562. Min Range: -5.2562

Max Act: 5.1625. Min Act: -0.1700

Data Index: 340903 (C4 (Web Text))

Max Activating Token Index: 675

Text #3

Max Range: 5.2562. Min Range: -5.2562

Max Act: 5.1312. Min Act: -0.1700

Data Index: 1030172 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 5.2562. Min Range: -5.2562

Max Act: 5.1625. Min Act: -0.1700

Data Index: 177477 (C4 (Web Text))

Max Activating Token Index: 662

Text #5

Max Range: 5.2562. Min Range: -5.2562

Max Act: 5.1000. Min Act: -0.1700

Data Index: 1128361 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 5.2562. Min Range: -5.2562

Max Act: 5.0687. Min Act: -0.1700

Data Index: 1156498 (C4 (Web Text))

Max Activating Token Index: 437

Text #7

Max Range: 5.2562. Min Range: -5.2562

Max Act: 5.0687. Min Act: -0.1700

Data Index: 625061 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 5.2562. Min Range: -5.2562

Max Act: 5.1625. Min Act: -0.1700

Data Index: 258473 (C4 (Web Text))

Max Activating Token Index: 843

Text #9

Max Range: 5.2562. Min Range: -5.2562

Max Act: 5.1000. Min Act: -0.1700

Data Index: 123539 (C4 (Web Text))

Max Activating Token Index: 945

Text #10

Max Range: 5.2562. Min Range: -5.2562

Max Act: 5.0687. Min Act: -0.1700

Data Index: 483268 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 5.2562. Min Range: -5.2562

Max Act: 5.0687. Min Act: -0.1700

Data Index: 659432 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 5.2562. Min Range: -5.2562

Max Act: 5.0687. Min Act: -0.1700

Data Index: 559228 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 5.2562. Min Range: -5.2562

Max Act: 5.0375. Min Act: -0.1700

Data Index: 837277 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 5.2562. Min Range: -5.2562

Max Act: 5.0375. Min Act: -0.1700

Data Index: 528268 (C4 (Web Text))

Max Activating Token Index: 573

Text #15

Max Range: 5.2562. Min Range: -5.2562

Max Act: 5.0687. Min Act: -0.1700

Data Index: 943921 (C4 (Web Text))

Max Activating Token Index: 609

Text #16

Max Range: 5.2562. Min Range: -5.2562

Max Act: 5.0687. Min Act: -0.1700

Data Index: 1047834 (C4 (Web Text))

Max Activating Token Index: 773

Text #17

Max Range: 5.2562. Min Range: -5.2562

Max Act: 5.0375. Min Act: -0.1700

Data Index: 1258437 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 5.2562. Min Range: -5.2562

Max Act: 5.0375. Min Act: -0.1700

Data Index: 728884 (C4 (Web Text))

Max Activating Token Index: 712

Text #19

Max Range: 5.2562. Min Range: -5.2562

Max Act: 5.0062. Min Act: -0.1700

Data Index: 548265 (C4 (Web Text))

Max Activating Token Index: 541