Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4586 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9837. Min Range: -6.9837
Max Act: 6.9837. Min Act: -0.1700
Data Index: 1495889 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9837. Min Range: -6.9837
Max Act: 6.8587. Min Act: -0.1700
Data Index: 4265066 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9837. Min Range: -6.9837
Max Act: 6.7962. Min Act: -0.1700
Data Index: 3497340 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9837. Min Range: -6.9837
Max Act: 6.7024. Min Act: -0.1700
Data Index: 5546171 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9837. Min Range: -6.9837
Max Act: 6.6087. Min Act: -0.1700
Data Index: 541690 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9837. Min Range: -6.9837
Max Act: 6.6087. Min Act: -0.1700
Data Index: 4155567 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9837. Min Range: -6.9837
Max Act: 6.5462. Min Act: -0.1700
Data Index: 4501313 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9837. Min Range: -6.9837
Max Act: 6.5774. Min Act: -0.1700
Data Index: 3622186 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9837. Min Range: -6.9837
Max Act: 6.5149. Min Act: -0.1700
Data Index: 674802 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9837. Min Range: -6.9837
Max Act: 6.5462. Min Act: -0.1700
Data Index: 4254440 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9837. Min Range: -6.9837
Max Act: 6.4837. Min Act: -0.1700
Data Index: 655495 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9837. Min Range: -6.9837
Max Act: 6.4524. Min Act: -0.1700
Data Index: 8721159 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9837. Min Range: -6.9837
Max Act: 6.5149. Min Act: -0.1700
Data Index: 6027053 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9837. Min Range: -6.9837
Max Act: 6.4524. Min Act: -0.1700
Data Index: 7537373 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9837. Min Range: -6.9837
Max Act: 6.4524. Min Act: -0.1700
Data Index: 8715852 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9837. Min Range: -6.9837
Max Act: 6.4212. Min Act: -0.1700
Data Index: 246390 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9837. Min Range: -6.9837
Max Act: 6.4524. Min Act: -0.1700
Data Index: 8211569 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9837. Min Range: -6.9837
Max Act: 6.4212. Min Act: -0.1700
Data Index: 8516712 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9837. Min Range: -6.9837
Max Act: 6.4212. Min Act: -0.1700
Data Index: 4836895 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9837. Min Range: -6.9837
Max Act: 6.4212. Min Act: -0.1700
Data Index: 2148455 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #19