Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3922 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7265. Min Range: -4.7265
Max Act: 4.7265. Min Act: -0.1700
Data Index: 3020459 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7265. Min Range: -4.7265
Max Act: 4.6327. Min Act: -0.1700
Data Index: 842466 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7265. Min Range: -4.7265
Max Act: 4.5702. Min Act: -0.1700
Data Index: 6021314 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7265. Min Range: -4.7265
Max Act: 4.5390. Min Act: -0.1700
Data Index: 6735199 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7265. Min Range: -4.7265
Max Act: 4.5390. Min Act: -0.1700
Data Index: 3289368 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7265. Min Range: -4.7265
Max Act: 4.5390. Min Act: -0.1700
Data Index: 1988579 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7265. Min Range: -4.7265
Max Act: 4.5390. Min Act: -0.1700
Data Index: 4858312 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7265. Min Range: -4.7265
Max Act: 4.5702. Min Act: -0.1700
Data Index: 4663433 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7265. Min Range: -4.7265
Max Act: 4.5390. Min Act: -0.1700
Data Index: 4547680 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7265. Min Range: -4.7265
Max Act: 4.5077. Min Act: -0.1700
Data Index: 761637 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7265. Min Range: -4.7265
Max Act: 4.5077. Min Act: -0.1700
Data Index: 4669754 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7265. Min Range: -4.7265
Max Act: 4.5077. Min Act: -0.1700
Data Index: 4711625 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7265. Min Range: -4.7265
Max Act: 4.5077. Min Act: -0.1700
Data Index: 2983182 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7265. Min Range: -4.7265
Max Act: 4.5077. Min Act: -0.1700
Data Index: 4669748 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7265. Min Range: -4.7265
Max Act: 4.5077. Min Act: -0.1700
Data Index: 4123106 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7265. Min Range: -4.7265
Max Act: 4.5390. Min Act: -0.1700
Data Index: 5505369 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7265. Min Range: -4.7265
Max Act: 4.5077. Min Act: -0.1700
Data Index: 3152373 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7265. Min Range: -4.7265
Max Act: 4.5077. Min Act: -0.1700
Data Index: 5532610 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7265. Min Range: -4.7265
Max Act: 4.5077. Min Act: -0.1700
Data Index: 5581406 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7265. Min Range: -4.7265
Max Act: 4.5077. Min Act: -0.1700
Data Index: 2300293 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #19