Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3693 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9370. Min Range: -5.9370
Max Act: 5.9370. Min Act: -0.1700
Data Index: 812529 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9370. Min Range: -5.9370
Max Act: 5.8432. Min Act: -0.1700
Data Index: 8093346 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9370. Min Range: -5.9370
Max Act: 5.8120. Min Act: -0.1700
Data Index: 8533984 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9370. Min Range: -5.9370
Max Act: 5.7807. Min Act: -0.1700
Data Index: 6194327 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9370. Min Range: -5.9370
Max Act: 5.6557. Min Act: -0.1700
Data Index: 6262485 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9370. Min Range: -5.9370
Max Act: 5.6245. Min Act: -0.1700
Data Index: 816423 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9370. Min Range: -5.9370
Max Act: 5.6245. Min Act: -0.1700
Data Index: 5477458 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9370. Min Range: -5.9370
Max Act: 5.5932. Min Act: -0.1700
Data Index: 2832461 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9370. Min Range: -5.9370
Max Act: 5.5932. Min Act: -0.1700
Data Index: 4604646 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9370. Min Range: -5.9370
Max Act: 5.5620. Min Act: -0.1700
Data Index: 2938995 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9370. Min Range: -5.9370
Max Act: 5.5307. Min Act: -0.1700
Data Index: 8802065 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9370. Min Range: -5.9370
Max Act: 5.4995. Min Act: -0.1700
Data Index: 2938994 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9370. Min Range: -5.9370
Max Act: 5.5307. Min Act: -0.1700
Data Index: 76242 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9370. Min Range: -5.9370
Max Act: 5.5307. Min Act: -0.1700
Data Index: 2989575 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9370. Min Range: -5.9370
Max Act: 5.4370. Min Act: -0.1700
Data Index: 6210703 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9370. Min Range: -5.9370
Max Act: 5.4057. Min Act: -0.1700
Data Index: 5800362 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9370. Min Range: -5.9370
Max Act: 5.4057. Min Act: -0.1700
Data Index: 7619834 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9370. Min Range: -5.9370
Max Act: 5.4057. Min Act: -0.1700
Data Index: 8829230 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9370. Min Range: -5.9370
Max Act: 5.4057. Min Act: -0.1700
Data Index: 2310881 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9370. Min Range: -5.9370
Max Act: 5.3745. Min Act: -0.1700
Data Index: 2562970 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #19