Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3662 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6573. Min Range: -6.6573
Max Act: 6.6573. Min Act: -0.1700
Data Index: 1362540 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6573. Min Range: -6.6573
Max Act: 6.5948. Min Act: -0.1700
Data Index: 8337102 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6573. Min Range: -6.6573
Max Act: 6.4073. Min Act: -0.1700
Data Index: 2182676 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6573. Min Range: -6.6573
Max Act: 6.2198. Min Act: -0.1700
Data Index: 7089591 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6573. Min Range: -6.6573
Max Act: 6.2198. Min Act: -0.1700
Data Index: 5479829 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6573. Min Range: -6.6573
Max Act: 6.1886. Min Act: -0.1700
Data Index: 5648016 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6573. Min Range: -6.6573
Max Act: 6.1261. Min Act: -0.1700
Data Index: 8355981 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6573. Min Range: -6.6573
Max Act: 6.0948. Min Act: -0.1700
Data Index: 8780837 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6573. Min Range: -6.6573
Max Act: 6.0636. Min Act: -0.1700
Data Index: 3147084 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6573. Min Range: -6.6573
Max Act: 6.0636. Min Act: -0.1700
Data Index: 3896850 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6573. Min Range: -6.6573
Max Act: 6.0636. Min Act: -0.1700
Data Index: 1664615 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6573. Min Range: -6.6573
Max Act: 6.0636. Min Act: -0.1700
Data Index: 8707116 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6573. Min Range: -6.6573
Max Act: 6.0636. Min Act: -0.1700
Data Index: 4983137 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6573. Min Range: -6.6573
Max Act: 5.9698. Min Act: -0.1700
Data Index: 2896219 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6573. Min Range: -6.6573
Max Act: 6.0011. Min Act: -0.1700
Data Index: 8128687 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6573. Min Range: -6.6573
Max Act: 6.0011. Min Act: -0.1700
Data Index: 5331559 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6573. Min Range: -6.6573
Max Act: 6.0011. Min Act: -0.1700
Data Index: 934483 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6573. Min Range: -6.6573
Max Act: 5.9698. Min Act: -0.1700
Data Index: 2219447 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6573. Min Range: -6.6573
Max Act: 5.9698. Min Act: -0.1700
Data Index: 7519683 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6573. Min Range: -6.6573
Max Act: 5.9698. Min Act: -0.1700
Data Index: 7275247 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #19