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

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

Neuron 1592 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: 3.8742. Min Range: -3.8742

Max Act: 3.8742. Min Act: -0.1700

Data Index: 1141867 (C4 (Web Text))

Max Activating Token Index: 610

Text #1

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.8429. Min Act: -0.1700

Data Index: 122712 (C4 (Web Text))

Max Activating Token Index: 580

Text #2

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.8429. Min Act: -0.1700

Data Index: 357419 (C4 (Web Text))

Max Activating Token Index: 462

Text #3

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.8429. Min Act: -0.1700

Data Index: 1163991 (C4 (Web Text))

Max Activating Token Index: 750

Text #4

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.8116. Min Act: -0.1700

Data Index: 1333018 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.7803. Min Act: -0.1700

Data Index: 1012736 (C4 (Web Text))

Max Activating Token Index: 535

Text #6

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.8116. Min Act: -0.1700

Data Index: 1051898 (C4 (Web Text))

Max Activating Token Index: 404

Text #7

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.7177. Min Act: -0.1700

Data Index: 227088 (C4 (Web Text))

Max Activating Token Index: 751

Text #8

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.7803. Min Act: -0.1700

Data Index: 483535 (C4 (Web Text))

Max Activating Token Index: 884

Text #9

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.7177. Min Act: -0.1700

Data Index: 373968 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.7177. Min Act: -0.1700

Data Index: 796521 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.7490. Min Act: -0.1700

Data Index: 1068498 (C4 (Web Text))

Max Activating Token Index: 718

Text #12

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.7490. Min Act: -0.1700

Data Index: 1059383 (C4 (Web Text))

Max Activating Token Index: 242

Text #13

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.7490. Min Act: -0.1700

Data Index: 801505 (C4 (Web Text))

Max Activating Token Index: 323

Text #14

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.7177. Min Act: -0.1700

Data Index: 746108 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.7177. Min Act: -0.1700

Data Index: 57571 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.7177. Min Act: -0.1700

Data Index: 744327 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.6865. Min Act: -0.1700

Data Index: 1022382 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.6865. Min Act: -0.1700

Data Index: 1048534 (C4 (Web Text))

Max Activating Token Index: 1006

Text #19

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.6865. Min Act: -0.1700

Data Index: 575487 (C4 (Web Text))

Max Activating Token Index: 568