Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 611 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1087. Min Range: -7.1087
Max Act: 7.1087. Min Act: -0.1700
Data Index: 6363177 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1087. Min Range: -7.1087
Max Act: 6.9837. Min Act: -0.1700
Data Index: 7628182 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1087. Min Range: -7.1087
Max Act: 6.8275. Min Act: -0.1700
Data Index: 8307671 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1087. Min Range: -7.1087
Max Act: 6.7962. Min Act: -0.1700
Data Index: 8324213 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1087. Min Range: -7.1087
Max Act: 6.7025. Min Act: -0.1700
Data Index: 6024956 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1087. Min Range: -7.1087
Max Act: 6.6400. Min Act: -0.1700
Data Index: 3538915 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1087. Min Range: -7.1087
Max Act: 6.6712. Min Act: -0.1700
Data Index: 3701948 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1087. Min Range: -7.1087
Max Act: 6.5775. Min Act: -0.1700
Data Index: 1881794 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1087. Min Range: -7.1087
Max Act: 6.5775. Min Act: -0.1700
Data Index: 2690837 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1087. Min Range: -7.1087
Max Act: 6.5462. Min Act: -0.1700
Data Index: 7678262 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1087. Min Range: -7.1087
Max Act: 6.5150. Min Act: -0.1700
Data Index: 2972436 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1087. Min Range: -7.1087
Max Act: 6.5150. Min Act: -0.1700
Data Index: 788575 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1087. Min Range: -7.1087
Max Act: 6.5150. Min Act: -0.1700
Data Index: 7733156 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1087. Min Range: -7.1087
Max Act: 6.4525. Min Act: -0.1700
Data Index: 4917492 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1087. Min Range: -7.1087
Max Act: 6.4837. Min Act: -0.1700
Data Index: 385662 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1087. Min Range: -7.1087
Max Act: 6.4525. Min Act: -0.1700
Data Index: 5029846 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1087. Min Range: -7.1087
Max Act: 6.4525. Min Act: -0.1700
Data Index: 2972437 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1087. Min Range: -7.1087
Max Act: 6.4525. Min Act: -0.1700
Data Index: 3252585 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1087. Min Range: -7.1087
Max Act: 6.4525. Min Act: -0.1700
Data Index: 6344615 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1087. Min Range: -7.1087
Max Act: 6.4525. Min Act: -0.1700
Data Index: 8331335 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #19