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

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

Neuron 249 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7594. Min Range: -3.7594

Max Act: 3.7594. Min Act: -0.1700

Data Index: 133023 (C4 (Web Text))

Max Activating Token Index: 953

Text #1

Max Range: 3.7594. Min Range: -3.7594

Max Act: 3.6812. Min Act: -0.1700

Data Index: 193460 (C4 (Web Text))

Max Activating Token Index: 782

Text #2

Max Range: 3.7594. Min Range: -3.7594

Max Act: 3.6029. Min Act: -0.1700

Data Index: 1290309 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 3.7594. Min Range: -3.7594

Max Act: 3.6499. Min Act: -0.1700

Data Index: 1335994 (C4 (Web Text))

Max Activating Token Index: 893

Text #4

Max Range: 3.7594. Min Range: -3.7594

Max Act: 3.6342. Min Act: -0.1700

Data Index: 1026663 (C4 (Web Text))

Max Activating Token Index: 757

Text #5

Max Range: 3.7594. Min Range: -3.7594

Max Act: 3.6186. Min Act: -0.1700

Data Index: 247661 (C4 (Web Text))

Max Activating Token Index: 613

Text #6

Max Range: 3.7594. Min Range: -3.7594

Max Act: 3.6186. Min Act: -0.1700

Data Index: 261295 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 3.7594. Min Range: -3.7594

Max Act: 3.6186. Min Act: -0.1700

Data Index: 409934 (C4 (Web Text))

Max Activating Token Index: 746

Text #8

Max Range: 3.7594. Min Range: -3.7594

Max Act: 3.5560. Min Act: -0.1700

Data Index: 520428 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 3.7594. Min Range: -3.7594

Max Act: 3.5716. Min Act: -0.1700

Data Index: 1277128 (C4 (Web Text))

Max Activating Token Index: 623

Text #10

Max Range: 3.7594. Min Range: -3.7594

Max Act: 3.5403. Min Act: -0.1700

Data Index: 1041031 (C4 (Web Text))

Max Activating Token Index: 662

Text #11

Max Range: 3.7594. Min Range: -3.7594

Max Act: 3.5246. Min Act: -0.1700

Data Index: 1345733 (C4 (Web Text))

Max Activating Token Index: 740

Text #12

Max Range: 3.7594. Min Range: -3.7594

Max Act: 3.5246. Min Act: -0.1700

Data Index: 160277 (C4 (Web Text))

Max Activating Token Index: 647

Text #13

Max Range: 3.7594. Min Range: -3.7594

Max Act: 3.5246. Min Act: -0.1700

Data Index: 385729 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 3.7594. Min Range: -3.7594

Max Act: 3.5246. Min Act: -0.1700

Data Index: 309684 (C4 (Web Text))

Max Activating Token Index: 326

Text #15

Max Range: 3.7594. Min Range: -3.7594

Max Act: 3.4933. Min Act: -0.1700

Data Index: 1136461 (C4 (Web Text))

Max Activating Token Index: 568

Text #16

Max Range: 3.7594. Min Range: -3.7594

Max Act: 3.4776. Min Act: -0.1700

Data Index: 257553 (C4 (Web Text))

Max Activating Token Index: 685

Text #17

Max Range: 3.7594. Min Range: -3.7594

Max Act: 3.4620. Min Act: -0.1700

Data Index: 1163507 (C4 (Web Text))

Max Activating Token Index: 374

Text #18

Max Range: 3.7594. Min Range: -3.7594

Max Act: 3.4776. Min Act: -0.1700

Data Index: 1257775 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 3.7594. Min Range: -3.7594

Max Act: 3.4306. Min Act: -0.1700

Data Index: 1175294 (C4 (Web Text))

Max Activating Token Index: 861