Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1683 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.7569. Min Range: -5.7569

Max Act: 5.7569. Min Act: -0.1700

Data Index: 521823 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 5.7569. Min Range: -5.7569

Max Act: 5.6007. Min Act: -0.1700

Data Index: 1131081 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 5.7569. Min Range: -5.7569

Max Act: 5.5069. Min Act: -0.1700

Data Index: 734717 (C4 (Web Text))

Max Activating Token Index: 537

Text #3

Max Range: 5.7569. Min Range: -5.7569

Max Act: 5.4444. Min Act: -0.1700

Data Index: 737168 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 5.7569. Min Range: -5.7569

Max Act: 5.5694. Min Act: -0.1700

Data Index: 938707 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 5.7569. Min Range: -5.7569

Max Act: 5.3507. Min Act: -0.1700

Data Index: 769553 (C4 (Web Text))

Max Activating Token Index: 885

Text #6

Max Range: 5.7569. Min Range: -5.7569

Max Act: 5.4132. Min Act: -0.1700

Data Index: 901194 (C4 (Web Text))

Max Activating Token Index: 453

Text #7

Max Range: 5.7569. Min Range: -5.7569

Max Act: 5.3819. Min Act: -0.1700

Data Index: 297005 (C4 (Web Text))

Max Activating Token Index: 570

Text #8

Max Range: 5.7569. Min Range: -5.7569

Max Act: 5.3819. Min Act: -0.1700

Data Index: 91908 (C4 (Web Text))

Max Activating Token Index: 897

Text #9

Max Range: 5.7569. Min Range: -5.7569

Max Act: 5.3819. Min Act: -0.1700

Data Index: 690369 (C4 (Web Text))

Max Activating Token Index: 145

Text #10

Max Range: 5.7569. Min Range: -5.7569

Max Act: 5.4132. Min Act: -0.1700

Data Index: 636499 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 5.7569. Min Range: -5.7569

Max Act: 5.3507. Min Act: -0.1700

Data Index: 750194 (C4 (Web Text))

Max Activating Token Index: 860

Text #12

Max Range: 5.7569. Min Range: -5.7569

Max Act: 5.4444. Min Act: -0.1700

Data Index: 153789 (C4 (Web Text))

Max Activating Token Index: 783

Text #13

Max Range: 5.7569. Min Range: -5.7569

Max Act: 5.3194. Min Act: -0.1700

Data Index: 357712 (C4 (Web Text))

Max Activating Token Index: 184

Text #14

Max Range: 5.7569. Min Range: -5.7569

Max Act: 5.3194. Min Act: -0.1700

Data Index: 1358293 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 5.7569. Min Range: -5.7569

Max Act: 5.2882. Min Act: -0.1700

Data Index: 172326 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 5.7569. Min Range: -5.7569

Max Act: 5.2882. Min Act: -0.1700

Data Index: 463718 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 5.7569. Min Range: -5.7569

Max Act: 5.3194. Min Act: -0.1700

Data Index: 450394 (C4 (Web Text))

Max Activating Token Index: 754

Text #18

Max Range: 5.7569. Min Range: -5.7569

Max Act: 5.3194. Min Act: -0.1700

Data Index: 560238 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 5.7569. Min Range: -5.7569

Max Act: 5.2569. Min Act: -0.1700

Data Index: 517112 (C4 (Web Text))

Max Activating Token Index: 796