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

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

Neuron 1267 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: 3.8742. Min Range: -3.8742

Max Act: 3.8742. Min Act: -0.1700

Data Index: 172663 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.6552. Min Act: -0.1700

Data Index: 975132 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.6552. Min Act: -0.1700

Data Index: 1105151 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.5926. Min Act: -0.1700

Data Index: 1029937 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.6239. Min Act: -0.1700

Data Index: 605225 (C4 (Web Text))

Max Activating Token Index: 392

Text #5

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.6865. Min Act: -0.1700

Data Index: 497505 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.5300. Min Act: -0.1700

Data Index: 344560 (C4 (Web Text))

Max Activating Token Index: 625

Text #7

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.4986. Min Act: -0.1700

Data Index: 1297139 (C4 (Web Text))

Max Activating Token Index: 881

Text #8

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.4673. Min Act: -0.1700

Data Index: 1178671 (C4 (Web Text))

Max Activating Token Index: 303

Text #9

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.4673. Min Act: -0.1700

Data Index: 62599 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.4673. Min Act: -0.1700

Data Index: 941541 (C4 (Web Text))

Max Activating Token Index: 127

Text #11

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.4986. Min Act: -0.1700

Data Index: 9988 (C4 (Web Text))

Max Activating Token Index: 833

Text #12

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.3732. Min Act: -0.1700

Data Index: 397450 (C4 (Web Text))

Max Activating Token Index: 394

Text #13

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.2790. Min Act: -0.1700

Data Index: 277634 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.3732. Min Act: -0.1700

Data Index: 97490 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.4359. Min Act: -0.1700

Data Index: 90006 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.4046. Min Act: -0.1700

Data Index: 1062606 (C4 (Web Text))

Max Activating Token Index: 194

Text #17

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.3732. Min Act: -0.1700

Data Index: 169505 (C4 (Web Text))

Max Activating Token Index: 472

Text #18

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.4046. Min Act: -0.1700

Data Index: 1088457 (C4 (Web Text))

Max Activating Token Index: 730

Text #19

Max Range: 3.8742. Min Range: -3.8742

Max Act: 3.2790. Min Act: -0.1700

Data Index: 628183 (C4 (Web Text))

Max Activating Token Index: 371