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

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

Neuron 832 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: 3.2266. Min Range: -3.2266

Max Act: 3.2266. Min Act: -0.1700

Data Index: 920515 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 3.2266. Min Range: -3.2266

Max Act: 3.1951. Min Act: -0.1700

Data Index: 212410 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 3.2266. Min Range: -3.2266

Max Act: 3.1951. Min Act: -0.1700

Data Index: 12750 (C4 (Web Text))

Max Activating Token Index: 757

Text #3

Max Range: 3.2266. Min Range: -3.2266

Max Act: 3.1794. Min Act: -0.1700

Data Index: 562543 (C4 (Web Text))

Max Activating Token Index: 680

Text #4

Max Range: 3.2266. Min Range: -3.2266

Max Act: 3.0691. Min Act: -0.1700

Data Index: 729305 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 3.2266. Min Range: -3.2266

Max Act: 3.0375. Min Act: -0.1700

Data Index: 570611 (C4 (Web Text))

Max Activating Token Index: 957

Text #6

Max Range: 3.2266. Min Range: -3.2266

Max Act: 3.0059. Min Act: -0.1700

Data Index: 390907 (C4 (Web Text))

Max Activating Token Index: 1015

Text #7

Max Range: 3.2266. Min Range: -3.2266

Max Act: 2.9901. Min Act: -0.1700

Data Index: 411488 (C4 (Web Text))

Max Activating Token Index: 838

Text #8

Max Range: 3.2266. Min Range: -3.2266

Max Act: 3.0217. Min Act: -0.1700

Data Index: 1175500 (C4 (Web Text))

Max Activating Token Index: 737

Text #9

Max Range: 3.2266. Min Range: -3.2266

Max Act: 3.0059. Min Act: -0.1700

Data Index: 305717 (C4 (Web Text))

Max Activating Token Index: 572

Text #10

Max Range: 3.2266. Min Range: -3.2266

Max Act: 2.9743. Min Act: -0.1700

Data Index: 799407 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 3.2266. Min Range: -3.2266

Max Act: 2.9584. Min Act: -0.1700

Data Index: 1264969 (C4 (Web Text))

Max Activating Token Index: 538

Text #12

Max Range: 3.2266. Min Range: -3.2266

Max Act: 2.9901. Min Act: -0.1700

Data Index: 296258 (C4 (Web Text))

Max Activating Token Index: 541

Text #13

Max Range: 3.2266. Min Range: -3.2266

Max Act: 2.9584. Min Act: -0.1700

Data Index: 124364 (C4 (Web Text))

Max Activating Token Index: 928

Text #14

Max Range: 3.2266. Min Range: -3.2266

Max Act: 2.9426. Min Act: -0.1700

Data Index: 1102460 (C4 (Web Text))

Max Activating Token Index: 968

Text #15

Max Range: 3.2266. Min Range: -3.2266

Max Act: 2.9426. Min Act: -0.1700

Data Index: 744251 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 3.2266. Min Range: -3.2266

Max Act: 3.0059. Min Act: -0.1700

Data Index: 321115 (C4 (Web Text))

Max Activating Token Index: 980

Text #17

Max Range: 3.2266. Min Range: -3.2266

Max Act: 2.9584. Min Act: -0.1700

Data Index: 360197 (C4 (Web Text))

Max Activating Token Index: 807

Text #18

Max Range: 3.2266. Min Range: -3.2266

Max Act: 2.9584. Min Act: -0.1700

Data Index: 512308 (C4 (Web Text))

Max Activating Token Index: 750

Text #19

Max Range: 3.2266. Min Range: -3.2266

Max Act: 2.9584. Min Act: -0.1700

Data Index: 291334 (C4 (Web Text))

Max Activating Token Index: 811