Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1457 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4653. Min Range: -7.4653
Max Act: 7.4653. Min Act: -0.1700
Data Index: 8824280 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4653. Min Range: -7.4653
Max Act: 7.0591. Min Act: -0.1700
Data Index: 4388554 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4653. Min Range: -7.4653
Max Act: 6.9966. Min Act: -0.1700
Data Index: 6427137 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4653. Min Range: -7.4653
Max Act: 6.9028. Min Act: -0.1700
Data Index: 1880297 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4653. Min Range: -7.4653
Max Act: 6.8716. Min Act: -0.1700
Data Index: 1022719 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4653. Min Range: -7.4653
Max Act: 6.7778. Min Act: -0.1700
Data Index: 1416157 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4653. Min Range: -7.4653
Max Act: 6.7466. Min Act: -0.1700
Data Index: 6749794 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4653. Min Range: -7.4653
Max Act: 6.6841. Min Act: -0.1700
Data Index: 3740128 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4653. Min Range: -7.4653
Max Act: 6.6841. Min Act: -0.1700
Data Index: 8174547 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4653. Min Range: -7.4653
Max Act: 6.6841. Min Act: -0.1700
Data Index: 7655647 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4653. Min Range: -7.4653
Max Act: 6.6528. Min Act: -0.1700
Data Index: 428113 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4653. Min Range: -7.4653
Max Act: 6.6528. Min Act: -0.1700
Data Index: 3517897 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4653. Min Range: -7.4653
Max Act: 6.6216. Min Act: -0.1700
Data Index: 635306 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4653. Min Range: -7.4653
Max Act: 6.6216. Min Act: -0.1700
Data Index: 8235390 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4653. Min Range: -7.4653
Max Act: 6.6216. Min Act: -0.1700
Data Index: 3195077 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4653. Min Range: -7.4653
Max Act: 6.6216. Min Act: -0.1700
Data Index: 6894302 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4653. Min Range: -7.4653
Max Act: 6.6216. Min Act: -0.1700
Data Index: 4611699 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4653. Min Range: -7.4653
Max Act: 6.6216. Min Act: -0.1700
Data Index: 6369691 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4653. Min Range: -7.4653
Max Act: 6.5903. Min Act: -0.1700
Data Index: 3053628 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4653. Min Range: -7.4653
Max Act: 6.5903. Min Act: -0.1700
Data Index: 1897737 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #19