Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2762 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3906. Min Range: -7.3906
Max Act: 7.3906. Min Act: -0.1700
Data Index: 6720741 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3906. Min Range: -7.3906
Max Act: 7.2031. Min Act: -0.1700
Data Index: 5899201 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3906. Min Range: -7.3906
Max Act: 7.0156. Min Act: -0.1700
Data Index: 5658156 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3906. Min Range: -7.3906
Max Act: 6.7969. Min Act: -0.1700
Data Index: 8542590 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3906. Min Range: -7.3906
Max Act: 6.7969. Min Act: -0.1700
Data Index: 6671640 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3906. Min Range: -7.3906
Max Act: 6.7656. Min Act: -0.1700
Data Index: 5728479 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3906. Min Range: -7.3906
Max Act: 6.7656. Min Act: -0.1700
Data Index: 5052004 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3906. Min Range: -7.3906
Max Act: 6.7344. Min Act: -0.1700
Data Index: 1791094 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3906. Min Range: -7.3906
Max Act: 6.7031. Min Act: -0.1700
Data Index: 4423608 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3906. Min Range: -7.3906
Max Act: 6.7031. Min Act: -0.1700
Data Index: 5872591 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3906. Min Range: -7.3906
Max Act: 6.6719. Min Act: -0.1700
Data Index: 462741 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3906. Min Range: -7.3906
Max Act: 6.6406. Min Act: -0.1700
Data Index: 6599166 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3906. Min Range: -7.3906
Max Act: 6.5781. Min Act: -0.1700
Data Index: 1165918 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3906. Min Range: -7.3906
Max Act: 6.6094. Min Act: -0.1700
Data Index: 8757186 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3906. Min Range: -7.3906
Max Act: 6.6094. Min Act: -0.1700
Data Index: 600536 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3906. Min Range: -7.3906
Max Act: 6.6094. Min Act: -0.1700
Data Index: 5680370 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3906. Min Range: -7.3906
Max Act: 6.5781. Min Act: -0.1700
Data Index: 4340745 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3906. Min Range: -7.3906
Max Act: 6.5156. Min Act: -0.1700
Data Index: 2981497 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3906. Min Range: -7.3906
Max Act: 6.5156. Min Act: -0.1700
Data Index: 6708408 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3906. Min Range: -7.3906
Max Act: 6.5156. Min Act: -0.1700
Data Index: 5436762 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19