Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5802 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8830. Min Range: -3.8830
Max Act: 3.8830. Min Act: -0.1700
Data Index: 5584640 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8830. Min Range: -3.8830
Max Act: 3.7267. Min Act: -0.1700
Data Index: 2636450 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8830. Min Range: -3.8830
Max Act: 3.6954. Min Act: -0.1700
Data Index: 4370998 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8830. Min Range: -3.8830
Max Act: 3.6172. Min Act: -0.1700
Data Index: 1978030 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8830. Min Range: -3.8830
Max Act: 3.5859. Min Act: -0.1700
Data Index: 8582292 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8830. Min Range: -3.8830
Max Act: 3.5859. Min Act: -0.1700
Data Index: 116807 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8830. Min Range: -3.8830
Max Act: 3.5859. Min Act: -0.1700
Data Index: 1310084 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8830. Min Range: -3.8830
Max Act: 3.5859. Min Act: -0.1700
Data Index: 860637 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8830. Min Range: -3.8830
Max Act: 3.5702. Min Act: -0.1700
Data Index: 3824123 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8830. Min Range: -3.8830
Max Act: 3.5859. Min Act: -0.1700
Data Index: 7416964 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8830. Min Range: -3.8830
Max Act: 3.5702. Min Act: -0.1700
Data Index: 7303657 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8830. Min Range: -3.8830
Max Act: 3.5389. Min Act: -0.1700
Data Index: 389738 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8830. Min Range: -3.8830
Max Act: 3.5076. Min Act: -0.1700
Data Index: 977707 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8830. Min Range: -3.8830
Max Act: 3.5076. Min Act: -0.1700
Data Index: 963388 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8830. Min Range: -3.8830
Max Act: 3.5076. Min Act: -0.1700
Data Index: 8633062 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8830. Min Range: -3.8830
Max Act: 3.4919. Min Act: -0.1700
Data Index: 2511178 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8830. Min Range: -3.8830
Max Act: 3.5076. Min Act: -0.1700
Data Index: 3222060 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8830. Min Range: -3.8830
Max Act: 3.5076. Min Act: -0.1700
Data Index: 602463 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8830. Min Range: -3.8830
Max Act: 3.4919. Min Act: -0.1700
Data Index: 4763925 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8830. Min Range: -3.8830
Max Act: 3.4762. Min Act: -0.1700
Data Index: 6721985 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19