Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3480 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1895. Min Range: -7.1895
Max Act: 7.1895. Min Act: -0.1700
Data Index: 1160690 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1895. Min Range: -7.1895
Max Act: 6.9708. Min Act: -0.1700
Data Index: 307466 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1895. Min Range: -7.1895
Max Act: 6.9395. Min Act: -0.1700
Data Index: 2929042 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1895. Min Range: -7.1895
Max Act: 6.9708. Min Act: -0.1700
Data Index: 7835737 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1895. Min Range: -7.1895
Max Act: 6.9083. Min Act: -0.1700
Data Index: 2682557 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1895. Min Range: -7.1895
Max Act: 6.9083. Min Act: -0.1700
Data Index: 8624171 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1895. Min Range: -7.1895
Max Act: 6.8458. Min Act: -0.1700
Data Index: 1322772 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1895. Min Range: -7.1895
Max Act: 6.8770. Min Act: -0.1700
Data Index: 4389192 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1895. Min Range: -7.1895
Max Act: 6.8770. Min Act: -0.1700
Data Index: 2712410 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1895. Min Range: -7.1895
Max Act: 6.7833. Min Act: -0.1700
Data Index: 7556134 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1895. Min Range: -7.1895
Max Act: 6.7520. Min Act: -0.1700
Data Index: 6671955 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1895. Min Range: -7.1895
Max Act: 6.7208. Min Act: -0.1700
Data Index: 528037 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1895. Min Range: -7.1895
Max Act: 6.7208. Min Act: -0.1700
Data Index: 7904731 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1895. Min Range: -7.1895
Max Act: 6.6583. Min Act: -0.1700
Data Index: 4484256 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1895. Min Range: -7.1895
Max Act: 6.6895. Min Act: -0.1700
Data Index: 3284942 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1895. Min Range: -7.1895
Max Act: 6.6583. Min Act: -0.1700
Data Index: 3217786 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1895. Min Range: -7.1895
Max Act: 6.6583. Min Act: -0.1700
Data Index: 4601565 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1895. Min Range: -7.1895
Max Act: 6.6583. Min Act: -0.1700
Data Index: 4087669 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1895. Min Range: -7.1895
Max Act: 6.6270. Min Act: -0.1700
Data Index: 4446093 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1895. Min Range: -7.1895
Max Act: 6.5958. Min Act: -0.1700
Data Index: 3238227 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #19