Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2665 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3130. Min Range: -8.3130
Max Act: 8.3130. Min Act: -0.1700
Data Index: 8067947 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3130. Min Range: -8.3130
Max Act: 8.2505. Min Act: -0.1700
Data Index: 4984585 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3130. Min Range: -8.3130
Max Act: 8.1255. Min Act: -0.1700
Data Index: 1863308 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3130. Min Range: -8.3130
Max Act: 8.1255. Min Act: -0.1700
Data Index: 3216521 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3130. Min Range: -8.3130
Max Act: 8.0942. Min Act: -0.1700
Data Index: 6347058 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3130. Min Range: -8.3130
Max Act: 8.0630. Min Act: -0.1700
Data Index: 1288626 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3130. Min Range: -8.3130
Max Act: 8.0005. Min Act: -0.1700
Data Index: 801503 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3130. Min Range: -8.3130
Max Act: 8.0005. Min Act: -0.1700
Data Index: 778595 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3130. Min Range: -8.3130
Max Act: 8.0005. Min Act: -0.1700
Data Index: 5366889 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3130. Min Range: -8.3130
Max Act: 7.9692. Min Act: -0.1700
Data Index: 151101 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3130. Min Range: -8.3130
Max Act: 7.9067. Min Act: -0.1700
Data Index: 1220067 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3130. Min Range: -8.3130
Max Act: 7.9067. Min Act: -0.1700
Data Index: 2167919 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3130. Min Range: -8.3130
Max Act: 7.9380. Min Act: -0.1700
Data Index: 5183890 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3130. Min Range: -8.3130
Max Act: 7.8755. Min Act: -0.1700
Data Index: 2903053 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3130. Min Range: -8.3130
Max Act: 7.8755. Min Act: -0.1700
Data Index: 4934995 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3130. Min Range: -8.3130
Max Act: 7.8442. Min Act: -0.1700
Data Index: 98777 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3130. Min Range: -8.3130
Max Act: 7.8130. Min Act: -0.1700
Data Index: 3275752 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3130. Min Range: -8.3130
Max Act: 7.8130. Min Act: -0.1700
Data Index: 8647707 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3130. Min Range: -8.3130
Max Act: 7.8130. Min Act: -0.1700
Data Index: 7054785 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3130. Min Range: -8.3130
Max Act: 7.7817. Min Act: -0.1700
Data Index: 3337739 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #19