Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3573 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8667. Min Range: -5.8667
Max Act: 5.8355. Min Act: -0.1700
Data Index: 1642256 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8667. Min Range: -5.8667
Max Act: 5.8667. Min Act: -0.1700
Data Index: 5071916 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8667. Min Range: -5.8667
Max Act: 5.8355. Min Act: -0.1700
Data Index: 88083 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8667. Min Range: -5.8667
Max Act: 5.8042. Min Act: -0.1700
Data Index: 5298238 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8667. Min Range: -5.8667
Max Act: 5.7417. Min Act: -0.1700
Data Index: 6449024 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8667. Min Range: -5.8667
Max Act: 5.7105. Min Act: -0.1700
Data Index: 5496135 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8667. Min Range: -5.8667
Max Act: 5.5855. Min Act: -0.1700
Data Index: 8249282 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8667. Min Range: -5.8667
Max Act: 5.5855. Min Act: -0.1700
Data Index: 3077837 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8667. Min Range: -5.8667
Max Act: 5.5855. Min Act: -0.1700
Data Index: 2328272 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8667. Min Range: -5.8667
Max Act: 5.5855. Min Act: -0.1700
Data Index: 1572015 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8667. Min Range: -5.8667
Max Act: 5.5230. Min Act: -0.1700
Data Index: 6521317 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8667. Min Range: -5.8667
Max Act: 5.5230. Min Act: -0.1700
Data Index: 505861 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8667. Min Range: -5.8667
Max Act: 5.4917. Min Act: -0.1700
Data Index: 2012548 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8667. Min Range: -5.8667
Max Act: 5.4605. Min Act: -0.1700
Data Index: 5708305 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8667. Min Range: -5.8667
Max Act: 5.4605. Min Act: -0.1700
Data Index: 4757199 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8667. Min Range: -5.8667
Max Act: 5.4605. Min Act: -0.1700
Data Index: 5290981 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8667. Min Range: -5.8667
Max Act: 5.4605. Min Act: -0.1700
Data Index: 1987272 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8667. Min Range: -5.8667
Max Act: 5.4292. Min Act: -0.1700
Data Index: 3622331 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8667. Min Range: -5.8667
Max Act: 5.4292. Min Act: -0.1700
Data Index: 7423207 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8667. Min Range: -5.8667
Max Act: 5.3667. Min Act: -0.1700
Data Index: 5002798 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19