Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1099 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.0538. Min Range: -5.0538

Max Act: 5.0372. Min Act: -0.1700

Data Index: 565198 (C4 (Web Text))

Max Activating Token Index: 446

Text #1

Max Range: 5.0538. Min Range: -5.0538

Max Act: 5.0167. Min Act: -0.1700

Data Index: 1475107 (Python Code)

Max Activating Token Index: 1004

Text #2

Max Range: 5.0538. Min Range: -5.0538

Max Act: 5.0538. Min Act: -0.1700

Data Index: 830744 (C4 (Web Text))

Max Activating Token Index: 1005

Text #3

Max Range: 5.0538. Min Range: -5.0538

Max Act: 5.0255. Min Act: -0.1700

Data Index: 144721 (C4 (Web Text))

Max Activating Token Index: 780

Text #4

Max Range: 5.0538. Min Range: -5.0538

Max Act: 4.9913. Min Act: -0.1700

Data Index: 854756 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 5.0538. Min Range: -5.0538

Max Act: 4.8751. Min Act: -0.1700

Data Index: 1513245 (Python Code)

Max Activating Token Index: 968

Text #6

Max Range: 5.0538. Min Range: -5.0538

Max Act: 4.8888. Min Act: -0.1700

Data Index: 1380675 (Python Code)

Max Activating Token Index: 950

Text #7

Max Range: 5.0538. Min Range: -5.0538

Max Act: 4.8868. Min Act: -0.1700

Data Index: 1579152 (Python Code)

Max Activating Token Index: 633

Text #8

Max Range: 5.0538. Min Range: -5.0538

Max Act: 4.8302. Min Act: -0.1700

Data Index: 1615617 (Python Code)

Max Activating Token Index: 339

Text #9

Max Range: 5.0538. Min Range: -5.0538

Max Act: 4.8282. Min Act: -0.1700

Data Index: 226426 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 5.0538. Min Range: -5.0538

Max Act: 4.8204. Min Act: -0.1700

Data Index: 381251 (C4 (Web Text))

Max Activating Token Index: 862

Text #11

Max Range: 5.0538. Min Range: -5.0538

Max Act: 4.8087. Min Act: -0.1700

Data Index: 1004691 (C4 (Web Text))

Max Activating Token Index: 745

Text #12

Max Range: 5.0538. Min Range: -5.0538

Max Act: 4.8380. Min Act: -0.1700

Data Index: 1202934 (C4 (Web Text))

Max Activating Token Index: 573

Text #13

Max Range: 5.0538. Min Range: -5.0538

Max Act: 4.8243. Min Act: -0.1700

Data Index: 508973 (C4 (Web Text))

Max Activating Token Index: 970

Text #14

Max Range: 5.0538. Min Range: -5.0538

Max Act: 4.7540. Min Act: -0.1700

Data Index: 558214 (C4 (Web Text))

Max Activating Token Index: 663

Text #15

Max Range: 5.0538. Min Range: -5.0538

Max Act: 4.7891. Min Act: -0.1700

Data Index: 825264 (C4 (Web Text))

Max Activating Token Index: 295

Text #16

Max Range: 5.0538. Min Range: -5.0538

Max Act: 4.7520. Min Act: -0.1700

Data Index: 228293 (C4 (Web Text))

Max Activating Token Index: 459

Text #17

Max Range: 5.0538. Min Range: -5.0538

Max Act: 4.7677. Min Act: -0.1700

Data Index: 823859 (C4 (Web Text))

Max Activating Token Index: 110

Text #18

Max Range: 5.0538. Min Range: -5.0538

Max Act: 4.7071. Min Act: -0.1700

Data Index: 1347628 (C4 (Web Text))

Max Activating Token Index: 619

Text #19

Max Range: 5.0538. Min Range: -5.0538

Max Act: 4.7208. Min Act: -0.1700

Data Index: 944218 (C4 (Web Text))

Max Activating Token Index: 105