Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2866 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4531. Min Range: -7.4531
Max Act: 7.4531. Min Act: -0.1700
Data Index: 3595838 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4531. Min Range: -7.4531
Max Act: 7.2031. Min Act: -0.1700
Data Index: 57250 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4531. Min Range: -7.4531
Max Act: 6.9843. Min Act: -0.1700
Data Index: 2950695 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4531. Min Range: -7.4531
Max Act: 6.9843. Min Act: -0.1700
Data Index: 5110433 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4531. Min Range: -7.4531
Max Act: 6.9531. Min Act: -0.1700
Data Index: 865946 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4531. Min Range: -7.4531
Max Act: 6.8281. Min Act: -0.1700
Data Index: 5221501 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4531. Min Range: -7.4531
Max Act: 6.8593. Min Act: -0.1700
Data Index: 3071788 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4531. Min Range: -7.4531
Max Act: 6.7968. Min Act: -0.1700
Data Index: 1245528 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4531. Min Range: -7.4531
Max Act: 6.7968. Min Act: -0.1700
Data Index: 6418686 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4531. Min Range: -7.4531
Max Act: 6.7656. Min Act: -0.1700
Data Index: 2654898 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4531. Min Range: -7.4531
Max Act: 6.7031. Min Act: -0.1700
Data Index: 6927333 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4531. Min Range: -7.4531
Max Act: 6.7031. Min Act: -0.1700
Data Index: 1194258 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4531. Min Range: -7.4531
Max Act: 6.6093. Min Act: -0.1700
Data Index: 1363543 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4531. Min Range: -7.4531
Max Act: 6.6093. Min Act: -0.1700
Data Index: 1008321 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4531. Min Range: -7.4531
Max Act: 6.5781. Min Act: -0.1700
Data Index: 7329121 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4531. Min Range: -7.4531
Max Act: 6.5781. Min Act: -0.1700
Data Index: 2869054 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4531. Min Range: -7.4531
Max Act: 6.5468. Min Act: -0.1700
Data Index: 5005424 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4531. Min Range: -7.4531
Max Act: 6.5781. Min Act: -0.1700
Data Index: 8150336 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4531. Min Range: -7.4531
Max Act: 6.5781. Min Act: -0.1700
Data Index: 4413019 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4531. Min Range: -7.4531
Max Act: 6.5468. Min Act: -0.1700
Data Index: 7908568 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #19