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

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

Neuron 1926 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: 5.8673. Min Range: -5.8673

Max Act: 5.8048. Min Act: -0.1700

Data Index: 899470 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 5.8673. Min Range: -5.8673

Max Act: 5.8361. Min Act: -0.1700

Data Index: 492587 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 5.8673. Min Range: -5.8673

Max Act: 5.8673. Min Act: -0.1700

Data Index: 708963 (C4 (Web Text))

Max Activating Token Index: 356

Text #3

Max Range: 5.8673. Min Range: -5.8673

Max Act: 5.8048. Min Act: -0.1700

Data Index: 616806 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 5.8673. Min Range: -5.8673

Max Act: 5.7423. Min Act: -0.1700

Data Index: 617466 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 5.8673. Min Range: -5.8673

Max Act: 5.7111. Min Act: -0.1700

Data Index: 412928 (C4 (Web Text))

Max Activating Token Index: 222

Text #6

Max Range: 5.8673. Min Range: -5.8673

Max Act: 5.6798. Min Act: -0.1700

Data Index: 1005846 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 5.8673. Min Range: -5.8673

Max Act: 5.7111. Min Act: -0.1700

Data Index: 684299 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 5.8673. Min Range: -5.8673

Max Act: 5.6486. Min Act: -0.1700

Data Index: 897426 (C4 (Web Text))

Max Activating Token Index: 794

Text #9

Max Range: 5.8673. Min Range: -5.8673

Max Act: 5.6486. Min Act: -0.1700

Data Index: 1077713 (C4 (Web Text))

Max Activating Token Index: 236

Text #10

Max Range: 5.8673. Min Range: -5.8673

Max Act: 5.7111. Min Act: -0.1700

Data Index: 760371 (C4 (Web Text))

Max Activating Token Index: 674

Text #11

Max Range: 5.8673. Min Range: -5.8673

Max Act: 5.6798. Min Act: -0.1700

Data Index: 967896 (C4 (Web Text))

Max Activating Token Index: 473

Text #12

Max Range: 5.8673. Min Range: -5.8673

Max Act: 5.6486. Min Act: -0.1700

Data Index: 222100 (C4 (Web Text))

Max Activating Token Index: 352

Text #13

Max Range: 5.8673. Min Range: -5.8673

Max Act: 5.6486. Min Act: -0.1700

Data Index: 473636 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 5.8673. Min Range: -5.8673

Max Act: 5.6173. Min Act: -0.1700

Data Index: 472000 (C4 (Web Text))

Max Activating Token Index: 584

Text #15

Max Range: 5.8673. Min Range: -5.8673

Max Act: 5.5861. Min Act: -0.1700

Data Index: 1046282 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 5.8673. Min Range: -5.8673

Max Act: 5.6173. Min Act: -0.1700

Data Index: 789147 (C4 (Web Text))

Max Activating Token Index: 407

Text #17

Max Range: 5.8673. Min Range: -5.8673

Max Act: 5.5861. Min Act: -0.1700

Data Index: 64017 (C4 (Web Text))

Max Activating Token Index: 369

Text #18

Max Range: 5.8673. Min Range: -5.8673

Max Act: 5.6173. Min Act: -0.1700

Data Index: 469102 (C4 (Web Text))

Max Activating Token Index: 401

Text #19

Max Range: 5.8673. Min Range: -5.8673

Max Act: 5.5861. Min Act: -0.1700

Data Index: 470611 (C4 (Web Text))

Max Activating Token Index: 651