Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3825 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3602. Min Range: -7.3602
Max Act: 7.3602. Min Act: -0.1700
Data Index: 3830091 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3602. Min Range: -7.3602
Max Act: 7.2977. Min Act: -0.1700
Data Index: 2547381 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3602. Min Range: -7.3602
Max Act: 7.2040. Min Act: -0.1700
Data Index: 4865996 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3602. Min Range: -7.3602
Max Act: 7.1415. Min Act: -0.1700
Data Index: 5616501 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3602. Min Range: -7.3602
Max Act: 7.1415. Min Act: -0.1700
Data Index: 2494419 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3602. Min Range: -7.3602
Max Act: 7.1415. Min Act: -0.1700
Data Index: 2968827 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3602. Min Range: -7.3602
Max Act: 7.1415. Min Act: -0.1700
Data Index: 1399451 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3602. Min Range: -7.3602
Max Act: 7.0790. Min Act: -0.1700
Data Index: 6196444 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3602. Min Range: -7.3602
Max Act: 7.1102. Min Act: -0.1700
Data Index: 7191669 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3602. Min Range: -7.3602
Max Act: 7.0790. Min Act: -0.1700
Data Index: 1694712 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3602. Min Range: -7.3602
Max Act: 7.0477. Min Act: -0.1700
Data Index: 782908 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3602. Min Range: -7.3602
Max Act: 7.0165. Min Act: -0.1700
Data Index: 3717107 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3602. Min Range: -7.3602
Max Act: 7.0165. Min Act: -0.1700
Data Index: 6279169 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3602. Min Range: -7.3602
Max Act: 6.9852. Min Act: -0.1700
Data Index: 513269 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3602. Min Range: -7.3602
Max Act: 6.9540. Min Act: -0.1700
Data Index: 1475354 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3602. Min Range: -7.3602
Max Act: 6.8915. Min Act: -0.1700
Data Index: 8810465 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3602. Min Range: -7.3602
Max Act: 6.9227. Min Act: -0.1700
Data Index: 7518217 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3602. Min Range: -7.3602
Max Act: 6.9227. Min Act: -0.1700
Data Index: 2438673 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3602. Min Range: -7.3602
Max Act: 6.8915. Min Act: -0.1700
Data Index: 640420 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3602. Min Range: -7.3602
Max Act: 6.8915. Min Act: -0.1700
Data Index: 1008891 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #19