Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 255 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7741. Min Range: -3.7741
Max Act: 3.7741. Min Act: -0.1700
Data Index: 5803561 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7741. Min Range: -3.7741
Max Act: 3.6959. Min Act: -0.1700
Data Index: 4809593 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7741. Min Range: -3.7741
Max Act: 3.6959. Min Act: -0.1700
Data Index: 5884962 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7741. Min Range: -3.7741
Max Act: 3.6959. Min Act: -0.1700
Data Index: 5284045 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7741. Min Range: -3.7741
Max Act: 3.6646. Min Act: -0.1700
Data Index: 5606254 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7741. Min Range: -3.7741
Max Act: 3.6334. Min Act: -0.1700
Data Index: 7601486 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7741. Min Range: -3.7741
Max Act: 3.6021. Min Act: -0.1700
Data Index: 1212460 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7741. Min Range: -3.7741
Max Act: 3.5707. Min Act: -0.1700
Data Index: 6415112 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7741. Min Range: -3.7741
Max Act: 3.5551. Min Act: -0.1700
Data Index: 868721 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7741. Min Range: -3.7741
Max Act: 3.5707. Min Act: -0.1700
Data Index: 6082589 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7741. Min Range: -3.7741
Max Act: 3.5238. Min Act: -0.1700
Data Index: 6991215 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7741. Min Range: -3.7741
Max Act: 3.5238. Min Act: -0.1700
Data Index: 5987557 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7741. Min Range: -3.7741
Max Act: 3.5238. Min Act: -0.1700
Data Index: 322900 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7741. Min Range: -3.7741
Max Act: 3.5081. Min Act: -0.1700
Data Index: 7421667 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7741. Min Range: -3.7741
Max Act: 3.4925. Min Act: -0.1700
Data Index: 6351737 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7741. Min Range: -3.7741
Max Act: 3.5081. Min Act: -0.1700
Data Index: 5691572 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7741. Min Range: -3.7741
Max Act: 3.4768. Min Act: -0.1700
Data Index: 2019306 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7741. Min Range: -3.7741
Max Act: 3.4925. Min Act: -0.1700
Data Index: 3920128 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7741. Min Range: -3.7741
Max Act: 3.4768. Min Act: -0.1700
Data Index: 2601830 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7741. Min Range: -3.7741
Max Act: 3.4925. Min Act: -0.1700
Data Index: 494840 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #19