Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 814 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3539. Min Range: -3.3539
Max Act: 3.3539. Min Act: -0.1700
Data Index: 3084205 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3539. Min Range: -3.3539
Max Act: 3.3539. Min Act: -0.1700
Data Index: 1007842 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3539. Min Range: -3.3539
Max Act: 3.3539. Min Act: -0.1700
Data Index: 5339000 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3539. Min Range: -3.3539
Max Act: 3.3225. Min Act: -0.1700
Data Index: 7900937 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3539. Min Range: -3.3539
Max Act: 3.3382. Min Act: -0.1700
Data Index: 6069181 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3539. Min Range: -3.3539
Max Act: 3.3382. Min Act: -0.1700
Data Index: 4448099 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3539. Min Range: -3.3539
Max Act: 3.3068. Min Act: -0.1700
Data Index: 7128426 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3539. Min Range: -3.3539
Max Act: 3.3068. Min Act: -0.1700
Data Index: 5140794 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3539. Min Range: -3.3539
Max Act: 3.3068. Min Act: -0.1700
Data Index: 4585079 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3539. Min Range: -3.3539
Max Act: 3.3068. Min Act: -0.1700
Data Index: 6721151 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3539. Min Range: -3.3539
Max Act: 3.2911. Min Act: -0.1700
Data Index: 3482641 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3539. Min Range: -3.3539
Max Act: 3.2911. Min Act: -0.1700
Data Index: 4718133 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3539. Min Range: -3.3539
Max Act: 3.2911. Min Act: -0.1700
Data Index: 8749283 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3539. Min Range: -3.3539
Max Act: 3.2911. Min Act: -0.1700
Data Index: 5318821 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3539. Min Range: -3.3539
Max Act: 3.2754. Min Act: -0.1699
Data Index: 2467761 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3539. Min Range: -3.3539
Max Act: 3.2597. Min Act: -0.1700
Data Index: 5686267 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3539. Min Range: -3.3539
Max Act: 3.2597. Min Act: -0.1700
Data Index: 720868 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3539. Min Range: -3.3539
Max Act: 3.2754. Min Act: -0.1700
Data Index: 2514262 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3539. Min Range: -3.3539
Max Act: 3.2597. Min Act: -0.1700
Data Index: 2894571 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3539. Min Range: -3.3539
Max Act: 3.2597. Min Act: -0.1700
Data Index: 6320683 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #19