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

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

Neuron 570 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8926. Min Range: -3.8926

Max Act: 3.8926. Min Act: -0.1700

Data Index: 946398 (C4 (Web Text))

Max Activating Token Index: 920

Text #1

Max Range: 3.8926. Min Range: -3.8926

Max Act: 3.7675. Min Act: -0.1700

Data Index: 309489 (C4 (Web Text))

Max Activating Token Index: 294

Text #2

Max Range: 3.8926. Min Range: -3.8926

Max Act: 3.7988. Min Act: -0.1700

Data Index: 229157 (C4 (Web Text))

Max Activating Token Index: 106

Text #3

Max Range: 3.8926. Min Range: -3.8926

Max Act: 3.7675. Min Act: -0.1700

Data Index: 1437935 (Python Code)

Max Activating Token Index: 88

Text #4

Max Range: 3.8926. Min Range: -3.8926

Max Act: 3.7362. Min Act: -0.1700

Data Index: 714513 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 3.8926. Min Range: -3.8926

Max Act: 3.7988. Min Act: -0.1700

Data Index: 278785 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 3.8926. Min Range: -3.8926

Max Act: 3.7362. Min Act: -0.1700

Data Index: 3672 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 3.8926. Min Range: -3.8926

Max Act: 3.6736. Min Act: -0.1700

Data Index: 1231670 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 3.8926. Min Range: -3.8926

Max Act: 3.7049. Min Act: -0.1700

Data Index: 752564 (C4 (Web Text))

Max Activating Token Index: 149

Text #9

Max Range: 3.8926. Min Range: -3.8926

Max Act: 3.7049. Min Act: -0.1700

Data Index: 360859 (C4 (Web Text))

Max Activating Token Index: 454

Text #10

Max Range: 3.8926. Min Range: -3.8926

Max Act: 3.7049. Min Act: -0.1700

Data Index: 1376242 (Python Code)

Max Activating Token Index: 52

Text #11

Max Range: 3.8926. Min Range: -3.8926

Max Act: 3.6736. Min Act: -0.1700

Data Index: 668029 (C4 (Web Text))

Max Activating Token Index: 275

Text #12

Max Range: 3.8926. Min Range: -3.8926

Max Act: 3.6423. Min Act: -0.1700

Data Index: 1293031 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 3.8926. Min Range: -3.8926

Max Act: 3.6423. Min Act: -0.1700

Data Index: 155177 (C4 (Web Text))

Max Activating Token Index: 568

Text #14

Max Range: 3.8926. Min Range: -3.8926

Max Act: 3.6736. Min Act: -0.1700

Data Index: 220870 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 3.8926. Min Range: -3.8926

Max Act: 3.6736. Min Act: -0.1700

Data Index: 184985 (C4 (Web Text))

Max Activating Token Index: 150

Text #16

Max Range: 3.8926. Min Range: -3.8926

Max Act: 3.6110. Min Act: -0.1700

Data Index: 1401025 (Python Code)

Max Activating Token Index: 893

Text #17

Max Range: 3.8926. Min Range: -3.8926

Max Act: 3.6110. Min Act: -0.1700

Data Index: 256391 (C4 (Web Text))

Max Activating Token Index: 491

Text #18

Max Range: 3.8926. Min Range: -3.8926

Max Act: 3.6110. Min Act: -0.1700

Data Index: 182405 (C4 (Web Text))

Max Activating Token Index: 603

Text #19

Max Range: 3.8926. Min Range: -3.8926

Max Act: 3.6110. Min Act: -0.1700

Data Index: 23356 (C4 (Web Text))

Max Activating Token Index: 690