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

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

Neuron 1516 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: 4.1120. Min Range: -4.1120

Max Act: 4.1120. Min Act: -0.1700

Data Index: 1272431 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 4.1120. Min Range: -4.1120

Max Act: 4.0494. Min Act: -0.1700

Data Index: 300498 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 4.1120. Min Range: -4.1120

Max Act: 3.8618. Min Act: -0.1700

Data Index: 1036353 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 4.1120. Min Range: -4.1120

Max Act: 3.7367. Min Act: -0.1700

Data Index: 686075 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 4.1120. Min Range: -4.1120

Max Act: 3.7680. Min Act: -0.1700

Data Index: 968970 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 4.1120. Min Range: -4.1120

Max Act: 3.7367. Min Act: -0.1700

Data Index: 1116442 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 4.1120. Min Range: -4.1120

Max Act: 3.7054. Min Act: -0.1700

Data Index: 820587 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 4.1120. Min Range: -4.1120

Max Act: 3.6428. Min Act: -0.1700

Data Index: 1159995 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 4.1120. Min Range: -4.1120

Max Act: 3.7367. Min Act: -0.1700

Data Index: 428198 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 4.1120. Min Range: -4.1120

Max Act: 3.7054. Min Act: -0.1700

Data Index: 952268 (C4 (Web Text))

Max Activating Token Index: 411

Text #10

Max Range: 4.1120. Min Range: -4.1120

Max Act: 3.7054. Min Act: -0.1700

Data Index: 716325 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 4.1120. Min Range: -4.1120

Max Act: 3.6741. Min Act: -0.1700

Data Index: 47568 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 4.1120. Min Range: -4.1120

Max Act: 3.6741. Min Act: -0.1700

Data Index: 419649 (C4 (Web Text))

Max Activating Token Index: 337

Text #13

Max Range: 4.1120. Min Range: -4.1120

Max Act: 3.6428. Min Act: -0.1700

Data Index: 1159384 (C4 (Web Text))

Max Activating Token Index: 292

Text #14

Max Range: 4.1120. Min Range: -4.1120

Max Act: 3.6741. Min Act: -0.1700

Data Index: 686526 (C4 (Web Text))

Max Activating Token Index: 689

Text #15

Max Range: 4.1120. Min Range: -4.1120

Max Act: 3.5958. Min Act: -0.1700

Data Index: 202830 (C4 (Web Text))

Max Activating Token Index: 382

Text #16

Max Range: 4.1120. Min Range: -4.1120

Max Act: 3.6115. Min Act: -0.1700

Data Index: 658958 (C4 (Web Text))

Max Activating Token Index: 837

Text #17

Max Range: 4.1120. Min Range: -4.1120

Max Act: 3.6741. Min Act: -0.1700

Data Index: 952455 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 4.1120. Min Range: -4.1120

Max Act: 3.6115. Min Act: -0.1700

Data Index: 331505 (C4 (Web Text))

Max Activating Token Index: 963

Text #19

Max Range: 4.1120. Min Range: -4.1120

Max Act: 3.6115. Min Act: -0.1700

Data Index: 930968 (C4 (Web Text))

Max Activating Token Index: 949