Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3226 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0080. Min Range: -7.0080
Max Act: 7.0080. Min Act: -0.1700
Data Index: 3641903 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0080. Min Range: -7.0080
Max Act: 6.9455. Min Act: -0.1700
Data Index: 1813553 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0080. Min Range: -7.0080
Max Act: 6.9142. Min Act: -0.1700
Data Index: 1187679 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0080. Min Range: -7.0080
Max Act: 6.9142. Min Act: -0.1700
Data Index: 3684532 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0080. Min Range: -7.0080
Max Act: 6.8830. Min Act: -0.1700
Data Index: 4224303 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0080. Min Range: -7.0080
Max Act: 6.7892. Min Act: -0.1700
Data Index: 2791462 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0080. Min Range: -7.0080
Max Act: 6.8205. Min Act: -0.1700
Data Index: 7058358 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0080. Min Range: -7.0080
Max Act: 6.7892. Min Act: -0.1700
Data Index: 2930333 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0080. Min Range: -7.0080
Max Act: 6.7892. Min Act: -0.1700
Data Index: 7656205 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0080. Min Range: -7.0080
Max Act: 6.7892. Min Act: -0.1700
Data Index: 8213600 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0080. Min Range: -7.0080
Max Act: 6.7580. Min Act: -0.1700
Data Index: 6409534 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0080. Min Range: -7.0080
Max Act: 6.7580. Min Act: -0.1700
Data Index: 3675676 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0080. Min Range: -7.0080
Max Act: 6.7580. Min Act: -0.1700
Data Index: 4798994 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0080. Min Range: -7.0080
Max Act: 6.7580. Min Act: -0.1700
Data Index: 3188234 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0080. Min Range: -7.0080
Max Act: 6.7267. Min Act: -0.1700
Data Index: 986324 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0080. Min Range: -7.0080
Max Act: 6.7267. Min Act: -0.1700
Data Index: 7006050 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0080. Min Range: -7.0080
Max Act: 6.7267. Min Act: -0.1700
Data Index: 2117258 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0080. Min Range: -7.0080
Max Act: 6.6955. Min Act: -0.1700
Data Index: 8576805 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0080. Min Range: -7.0080
Max Act: 6.6642. Min Act: -0.1700
Data Index: 975301 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0080. Min Range: -7.0080
Max Act: 6.6642. Min Act: -0.1700
Data Index: 1603335 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19