Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4525 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5870. Min Range: -7.5870
Max Act: 7.5870. Min Act: -0.1700
Data Index: 5708896 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5870. Min Range: -7.5870
Max Act: 6.6808. Min Act: -0.1700
Data Index: 266820 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5870. Min Range: -7.5870
Max Act: 6.6808. Min Act: -0.1700
Data Index: 1455925 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5870. Min Range: -7.5870
Max Act: 6.5870. Min Act: -0.1700
Data Index: 5098641 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5870. Min Range: -7.5870
Max Act: 6.3370. Min Act: -0.1700
Data Index: 3164402 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5870. Min Range: -7.5870
Max Act: 6.3370. Min Act: -0.1700
Data Index: 8078663 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5870. Min Range: -7.5870
Max Act: 6.3370. Min Act: -0.1700
Data Index: 7799976 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5870. Min Range: -7.5870
Max Act: 6.3058. Min Act: -0.1700
Data Index: 2997307 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5870. Min Range: -7.5870
Max Act: 6.2433. Min Act: -0.1700
Data Index: 8005219 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5870. Min Range: -7.5870
Max Act: 6.2745. Min Act: -0.1700
Data Index: 7104951 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5870. Min Range: -7.5870
Max Act: 6.2433. Min Act: -0.1700
Data Index: 7149893 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5870. Min Range: -7.5870
Max Act: 6.2120. Min Act: -0.1700
Data Index: 18583 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5870. Min Range: -7.5870
Max Act: 6.2120. Min Act: -0.1700
Data Index: 742011 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5870. Min Range: -7.5870
Max Act: 6.1808. Min Act: -0.1700
Data Index: 1723515 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5870. Min Range: -7.5870
Max Act: 6.1808. Min Act: -0.1700
Data Index: 3179136 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5870. Min Range: -7.5870
Max Act: 6.1808. Min Act: -0.1700
Data Index: 1767662 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5870. Min Range: -7.5870
Max Act: 6.1495. Min Act: -0.1700
Data Index: 8443300 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5870. Min Range: -7.5870
Max Act: 6.1183. Min Act: -0.1700
Data Index: 3859337 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5870. Min Range: -7.5870
Max Act: 6.1183. Min Act: -0.1700
Data Index: 4120013 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5870. Min Range: -7.5870
Max Act: 6.0870. Min Act: -0.1700
Data Index: 4056064 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #19