Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5975 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8923. Min Range: -6.8923
Max Act: 6.8923. Min Act: -0.1700
Data Index: 3198049 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8923. Min Range: -6.8923
Max Act: 6.5798. Min Act: -0.1700
Data Index: 7965168 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8923. Min Range: -6.8923
Max Act: 6.5798. Min Act: -0.1700
Data Index: 3057933 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8923. Min Range: -6.8923
Max Act: 6.5173. Min Act: -0.1700
Data Index: 4232640 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8923. Min Range: -6.8923
Max Act: 6.4548. Min Act: -0.1700
Data Index: 7067559 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8923. Min Range: -6.8923
Max Act: 6.4236. Min Act: -0.1700
Data Index: 2582262 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8923. Min Range: -6.8923
Max Act: 6.4236. Min Act: -0.1700
Data Index: 1046873 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8923. Min Range: -6.8923
Max Act: 6.3611. Min Act: -0.1700
Data Index: 7574499 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8923. Min Range: -6.8923
Max Act: 6.3611. Min Act: -0.1700
Data Index: 1123558 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8923. Min Range: -6.8923
Max Act: 6.3298. Min Act: -0.1700
Data Index: 7986404 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8923. Min Range: -6.8923
Max Act: 6.2986. Min Act: -0.1700
Data Index: 4274989 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8923. Min Range: -6.8923
Max Act: 6.2986. Min Act: -0.1700
Data Index: 7948398 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8923. Min Range: -6.8923
Max Act: 6.2986. Min Act: -0.1700
Data Index: 5299944 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8923. Min Range: -6.8923
Max Act: 6.2361. Min Act: -0.1700
Data Index: 4163646 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8923. Min Range: -6.8923
Max Act: 6.2986. Min Act: -0.1700
Data Index: 7379821 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8923. Min Range: -6.8923
Max Act: 6.2048. Min Act: -0.1700
Data Index: 2569999 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8923. Min Range: -6.8923
Max Act: 6.1736. Min Act: -0.1700
Data Index: 3398917 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8923. Min Range: -6.8923
Max Act: 6.1736. Min Act: -0.1700
Data Index: 8244566 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8923. Min Range: -6.8923
Max Act: 6.1423. Min Act: -0.1700
Data Index: 5816984 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8923. Min Range: -6.8923
Max Act: 6.1423. Min Act: -0.1700
Data Index: 7683547 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #19