Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 638 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0203. Min Range: -6.0203
Max Act: 6.0203. Min Act: -0.1700
Data Index: 1566640 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0203. Min Range: -6.0203
Max Act: 5.9265. Min Act: -0.1700
Data Index: 1131525 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0203. Min Range: -6.0203
Max Act: 5.8953. Min Act: -0.1700
Data Index: 7515308 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0203. Min Range: -6.0203
Max Act: 5.8640. Min Act: -0.1700
Data Index: 1276585 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0203. Min Range: -6.0203
Max Act: 5.8640. Min Act: -0.1700
Data Index: 2494810 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0203. Min Range: -6.0203
Max Act: 5.8328. Min Act: -0.1700
Data Index: 7552779 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0203. Min Range: -6.0203
Max Act: 5.8328. Min Act: -0.1700
Data Index: 3171181 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0203. Min Range: -6.0203
Max Act: 5.8015. Min Act: -0.1700
Data Index: 8225129 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0203. Min Range: -6.0203
Max Act: 5.8328. Min Act: -0.1700
Data Index: 491511 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0203. Min Range: -6.0203
Max Act: 5.7703. Min Act: -0.1700
Data Index: 5130849 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0203. Min Range: -6.0203
Max Act: 5.7390. Min Act: -0.1700
Data Index: 1215070 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0203. Min Range: -6.0203
Max Act: 5.7078. Min Act: -0.1700
Data Index: 7552782 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0203. Min Range: -6.0203
Max Act: 5.7078. Min Act: -0.1700
Data Index: 4198562 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0203. Min Range: -6.0203
Max Act: 5.6765. Min Act: -0.1700
Data Index: 3020041 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0203. Min Range: -6.0203
Max Act: 5.6765. Min Act: -0.1700
Data Index: 6464557 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0203. Min Range: -6.0203
Max Act: 5.6765. Min Act: -0.1700
Data Index: 1647567 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0203. Min Range: -6.0203
Max Act: 5.6453. Min Act: -0.1700
Data Index: 6665622 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0203. Min Range: -6.0203
Max Act: 5.6453. Min Act: -0.1700
Data Index: 1677952 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0203. Min Range: -6.0203
Max Act: 5.6140. Min Act: -0.1700
Data Index: 721027 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0203. Min Range: -6.0203
Max Act: 5.6140. Min Act: -0.1700
Data Index: 2653367 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #19