Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 866 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4746. Min Range: -4.4746
Max Act: 4.4746. Min Act: -0.1700
Data Index: 2952892 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4746. Min Range: -4.4746
Max Act: 4.3495. Min Act: -0.1700
Data Index: 7516536 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4746. Min Range: -4.4746
Max Act: 4.3183. Min Act: -0.1700
Data Index: 1478864 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4746. Min Range: -4.4746
Max Act: 4.3495. Min Act: -0.1700
Data Index: 3177854 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4746. Min Range: -4.4746
Max Act: 4.2870. Min Act: -0.1700
Data Index: 5995656 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4746. Min Range: -4.4746
Max Act: 4.2558. Min Act: -0.1700
Data Index: 7912265 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4746. Min Range: -4.4746
Max Act: 4.2558. Min Act: -0.1700
Data Index: 301702 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4746. Min Range: -4.4746
Max Act: 4.2558. Min Act: -0.1700
Data Index: 2024675 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4746. Min Range: -4.4746
Max Act: 4.2558. Min Act: -0.1700
Data Index: 4319997 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4746. Min Range: -4.4746
Max Act: 4.1933. Min Act: -0.1700
Data Index: 7844366 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4746. Min Range: -4.4746
Max Act: 4.1620. Min Act: -0.1700
Data Index: 5134911 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4746. Min Range: -4.4746
Max Act: 4.1620. Min Act: -0.1700
Data Index: 268196 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4746. Min Range: -4.4746
Max Act: 4.1308. Min Act: -0.1700
Data Index: 3846916 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4746. Min Range: -4.4746
Max Act: 4.1620. Min Act: -0.1700
Data Index: 4787415 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4746. Min Range: -4.4746
Max Act: 4.0995. Min Act: -0.1700
Data Index: 6539717 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4746. Min Range: -4.4746
Max Act: 4.0995. Min Act: -0.1700
Data Index: 3683577 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4746. Min Range: -4.4746
Max Act: 4.0683. Min Act: -0.1700
Data Index: 2069566 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4746. Min Range: -4.4746
Max Act: 4.0370. Min Act: -0.1700
Data Index: 4364760 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4746. Min Range: -4.4746
Max Act: 4.0370. Min Act: -0.1700
Data Index: 2736580 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4746. Min Range: -4.4746
Max Act: 4.0370. Min Act: -0.1700
Data Index: 2007087 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #19