Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1866 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1050. Min Range: -5.1050
Max Act: 5.1050. Min Act: -0.1700
Data Index: 3936081 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1050. Min Range: -5.1050
Max Act: 5.0425. Min Act: -0.1700
Data Index: 1812962 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1050. Min Range: -5.1050
Max Act: 4.9800. Min Act: -0.1700
Data Index: 7031178 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1050. Min Range: -5.1050
Max Act: 4.9487. Min Act: -0.1700
Data Index: 3491843 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1050. Min Range: -5.1050
Max Act: 4.9175. Min Act: -0.1700
Data Index: 4869214 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1050. Min Range: -5.1050
Max Act: 4.9175. Min Act: -0.1700
Data Index: 297911 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1050. Min Range: -5.1050
Max Act: 4.8862. Min Act: -0.1700
Data Index: 4708 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1050. Min Range: -5.1050
Max Act: 4.7925. Min Act: -0.1700
Data Index: 3097724 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1050. Min Range: -5.1050
Max Act: 4.7612. Min Act: -0.1700
Data Index: 8605285 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1050. Min Range: -5.1050
Max Act: 4.7612. Min Act: -0.1700
Data Index: 3469824 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1050. Min Range: -5.1050
Max Act: 4.7612. Min Act: -0.1700
Data Index: 8601169 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1050. Min Range: -5.1050
Max Act: 4.7612. Min Act: -0.1700
Data Index: 8303475 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1050. Min Range: -5.1050
Max Act: 4.6987. Min Act: -0.1700
Data Index: 7451663 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1050. Min Range: -5.1050
Max Act: 4.6362. Min Act: -0.1700
Data Index: 3057286 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1050. Min Range: -5.1050
Max Act: 4.6675. Min Act: -0.1700
Data Index: 5156461 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1050. Min Range: -5.1050
Max Act: 4.6675. Min Act: -0.1700
Data Index: 6304646 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1050. Min Range: -5.1050
Max Act: 4.6362. Min Act: -0.1700
Data Index: 3270166 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1050. Min Range: -5.1050
Max Act: 4.6362. Min Act: -0.1700
Data Index: 4339645 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1050. Min Range: -5.1050
Max Act: 4.6362. Min Act: -0.1700
Data Index: 8484661 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1050. Min Range: -5.1050
Max Act: 4.6050. Min Act: -0.1700
Data Index: 1587839 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19