Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2978 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2061. Min Range: -6.2061
Max Act: 6.2061. Min Act: -0.1700
Data Index: 1626939 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2061. Min Range: -6.2061
Max Act: 6.1124. Min Act: -0.1700
Data Index: 2603900 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2061. Min Range: -6.2061
Max Act: 6.0811. Min Act: -0.1700
Data Index: 7299263 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2061. Min Range: -6.2061
Max Act: 6.0186. Min Act: -0.1700
Data Index: 1831566 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2061. Min Range: -6.2061
Max Act: 6.0186. Min Act: -0.1700
Data Index: 105028 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2061. Min Range: -6.2061
Max Act: 5.9874. Min Act: -0.1700
Data Index: 6098930 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2061. Min Range: -6.2061
Max Act: 5.9561. Min Act: -0.1700
Data Index: 7180177 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2061. Min Range: -6.2061
Max Act: 5.8624. Min Act: -0.1700
Data Index: 4527115 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2061. Min Range: -6.2061
Max Act: 5.8936. Min Act: -0.1700
Data Index: 3002173 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2061. Min Range: -6.2061
Max Act: 5.8624. Min Act: -0.1700
Data Index: 87817 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2061. Min Range: -6.2061
Max Act: 5.8624. Min Act: -0.1700
Data Index: 7140865 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2061. Min Range: -6.2061
Max Act: 5.8311. Min Act: -0.1700
Data Index: 7998894 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2061. Min Range: -6.2061
Max Act: 5.8311. Min Act: -0.1700
Data Index: 3736009 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2061. Min Range: -6.2061
Max Act: 5.7686. Min Act: -0.1700
Data Index: 4942284 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2061. Min Range: -6.2061
Max Act: 5.7686. Min Act: -0.1700
Data Index: 6970112 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2061. Min Range: -6.2061
Max Act: 5.7999. Min Act: -0.1700
Data Index: 5721725 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2061. Min Range: -6.2061
Max Act: 5.7686. Min Act: -0.1700
Data Index: 2168084 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2061. Min Range: -6.2061
Max Act: 5.7374. Min Act: -0.1700
Data Index: 3603526 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2061. Min Range: -6.2061
Max Act: 5.7686. Min Act: -0.1700
Data Index: 7367168 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2061. Min Range: -6.2061
Max Act: 5.7374. Min Act: -0.1700
Data Index: 2881259 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19