Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3248 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6337. Min Range: -6.6337
Max Act: 6.6337. Min Act: -0.1700
Data Index: 240539 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6337. Min Range: -6.6337
Max Act: 6.3837. Min Act: -0.1700
Data Index: 3346943 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6337. Min Range: -6.6337
Max Act: 6.1962. Min Act: -0.1700
Data Index: 3644448 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6337. Min Range: -6.6337
Max Act: 6.2274. Min Act: -0.1700
Data Index: 3618762 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6337. Min Range: -6.6337
Max Act: 6.1649. Min Act: -0.1700
Data Index: 3368400 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6337. Min Range: -6.6337
Max Act: 6.1649. Min Act: -0.1700
Data Index: 232242 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6337. Min Range: -6.6337
Max Act: 6.1337. Min Act: -0.1700
Data Index: 6452369 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6337. Min Range: -6.6337
Max Act: 6.1337. Min Act: -0.1700
Data Index: 7190325 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6337. Min Range: -6.6337
Max Act: 6.1337. Min Act: -0.1700
Data Index: 7451526 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6337. Min Range: -6.6337
Max Act: 6.1024. Min Act: -0.1700
Data Index: 15927 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6337. Min Range: -6.6337
Max Act: 6.1024. Min Act: -0.1700
Data Index: 5669825 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6337. Min Range: -6.6337
Max Act: 6.1024. Min Act: -0.1700
Data Index: 8527417 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6337. Min Range: -6.6337
Max Act: 6.1024. Min Act: -0.1700
Data Index: 4109338 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6337. Min Range: -6.6337
Max Act: 6.1024. Min Act: -0.1700
Data Index: 3463573 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6337. Min Range: -6.6337
Max Act: 6.0712. Min Act: -0.1700
Data Index: 5527549 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6337. Min Range: -6.6337
Max Act: 6.0712. Min Act: -0.1700
Data Index: 2988729 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6337. Min Range: -6.6337
Max Act: 6.0712. Min Act: -0.1700
Data Index: 400181 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6337. Min Range: -6.6337
Max Act: 6.0712. Min Act: -0.1700
Data Index: 6860523 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6337. Min Range: -6.6337
Max Act: 6.0399. Min Act: -0.1700
Data Index: 7410240 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6337. Min Range: -6.6337
Max Act: 6.0399. Min Act: -0.1700
Data Index: 3145737 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #19