Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2889 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0137. Min Range: -4.0137
Max Act: 4.0137. Min Act: -0.1700
Data Index: 7724338 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0137. Min Range: -4.0137
Max Act: 3.9824. Min Act: -0.1700
Data Index: 3404679 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0137. Min Range: -4.0137
Max Act: 3.9199. Min Act: -0.1700
Data Index: 1993848 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0137. Min Range: -4.0137
Max Act: 3.8886. Min Act: -0.1700
Data Index: 7438762 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0137. Min Range: -4.0137
Max Act: 3.8886. Min Act: -0.1700
Data Index: 4658738 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0137. Min Range: -4.0137
Max Act: 3.7948. Min Act: -0.1700
Data Index: 3850195 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0137. Min Range: -4.0137
Max Act: 3.7948. Min Act: -0.1700
Data Index: 7770991 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0137. Min Range: -4.0137
Max Act: 3.7948. Min Act: -0.1700
Data Index: 6484821 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0137. Min Range: -4.0137
Max Act: 3.7948. Min Act: -0.1700
Data Index: 5444796 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0137. Min Range: -4.0137
Max Act: 3.7948. Min Act: -0.1700
Data Index: 5064901 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0137. Min Range: -4.0137
Max Act: 3.7635. Min Act: -0.1700
Data Index: 6334362 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0137. Min Range: -4.0137
Max Act: 3.7635. Min Act: -0.1700
Data Index: 7437196 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0137. Min Range: -4.0137
Max Act: 3.7323. Min Act: -0.1700
Data Index: 2039962 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0137. Min Range: -4.0137
Max Act: 3.7635. Min Act: -0.1700
Data Index: 8166939 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0137. Min Range: -4.0137
Max Act: 3.7635. Min Act: -0.1700
Data Index: 3059708 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0137. Min Range: -4.0137
Max Act: 3.7010. Min Act: -0.1700
Data Index: 3346605 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0137. Min Range: -4.0137
Max Act: 3.7323. Min Act: -0.1700
Data Index: 7789564 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0137. Min Range: -4.0137
Max Act: 3.7323. Min Act: -0.1700
Data Index: 4865594 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0137. Min Range: -4.0137
Max Act: 3.7323. Min Act: -0.1700
Data Index: 3404678 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0137. Min Range: -4.0137
Max Act: 3.7010. Min Act: -0.1700
Data Index: 4558568 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #19