Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3384 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7871. Min Range: -5.7871
Max Act: 5.7871. Min Act: -0.1700
Data Index: 8641470 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7871. Min Range: -5.7871
Max Act: 5.6933. Min Act: -0.1700
Data Index: 5532797 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7871. Min Range: -5.7871
Max Act: 5.6933. Min Act: -0.1700
Data Index: 7526729 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7871. Min Range: -5.7871
Max Act: 5.6308. Min Act: -0.1700
Data Index: 5568752 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7871. Min Range: -5.7871
Max Act: 5.5683. Min Act: -0.1700
Data Index: 5139897 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7871. Min Range: -5.7871
Max Act: 5.5683. Min Act: -0.1700
Data Index: 3884363 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7871. Min Range: -5.7871
Max Act: 5.5683. Min Act: -0.1700
Data Index: 7931150 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7871. Min Range: -5.7871
Max Act: 5.5371. Min Act: -0.1700
Data Index: 6406153 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7871. Min Range: -5.7871
Max Act: 5.5371. Min Act: -0.1700
Data Index: 404965 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7871. Min Range: -5.7871
Max Act: 5.5058. Min Act: -0.1700
Data Index: 2272342 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7871. Min Range: -5.7871
Max Act: 5.5058. Min Act: -0.1700
Data Index: 6365043 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7871. Min Range: -5.7871
Max Act: 5.4746. Min Act: -0.1700
Data Index: 5751892 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7871. Min Range: -5.7871
Max Act: 5.4746. Min Act: -0.1700
Data Index: 3114685 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7871. Min Range: -5.7871
Max Act: 5.4433. Min Act: -0.1700
Data Index: 1113192 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7871. Min Range: -5.7871
Max Act: 5.4121. Min Act: -0.1700
Data Index: 4430849 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7871. Min Range: -5.7871
Max Act: 5.4121. Min Act: -0.1700
Data Index: 2581610 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7871. Min Range: -5.7871
Max Act: 5.4433. Min Act: -0.1700
Data Index: 1610871 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7871. Min Range: -5.7871
Max Act: 5.4121. Min Act: -0.1700
Data Index: 4565781 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7871. Min Range: -5.7871
Max Act: 5.3808. Min Act: -0.1700
Data Index: 4322623 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7871. Min Range: -5.7871
Max Act: 5.4121. Min Act: -0.1700
Data Index: 5970020 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #19