Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2813 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7185. Min Range: -5.7185
Max Act: 5.6872. Min Act: -0.1700
Data Index: 4045376 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7185. Min Range: -5.7185
Max Act: 5.6872. Min Act: -0.1700
Data Index: 3312697 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7185. Min Range: -5.7185
Max Act: 5.7185. Min Act: -0.1700
Data Index: 2365857 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7185. Min Range: -5.7185
Max Act: 5.7185. Min Act: -0.1700
Data Index: 3529017 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7185. Min Range: -5.7185
Max Act: 5.6872. Min Act: -0.1700
Data Index: 3650372 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7185. Min Range: -5.7185
Max Act: 5.6872. Min Act: -0.1700
Data Index: 7184227 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7185. Min Range: -5.7185
Max Act: 5.6560. Min Act: -0.1700
Data Index: 8130631 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7185. Min Range: -5.7185
Max Act: 5.6560. Min Act: -0.1700
Data Index: 2987372 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7185. Min Range: -5.7185
Max Act: 5.6560. Min Act: -0.1700
Data Index: 7744558 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7185. Min Range: -5.7185
Max Act: 5.6560. Min Act: -0.1700
Data Index: 5619130 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7185. Min Range: -5.7185
Max Act: 5.6247. Min Act: -0.1700
Data Index: 5852732 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7185. Min Range: -5.7185
Max Act: 5.6247. Min Act: -0.1700
Data Index: 808078 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7185. Min Range: -5.7185
Max Act: 5.5622. Min Act: -0.1700
Data Index: 6870644 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7185. Min Range: -5.7185
Max Act: 5.5622. Min Act: -0.1700
Data Index: 5446475 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7185. Min Range: -5.7185
Max Act: 5.5310. Min Act: -0.1700
Data Index: 3436399 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7185. Min Range: -5.7185
Max Act: 5.5310. Min Act: -0.1700
Data Index: 2344330 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7185. Min Range: -5.7185
Max Act: 5.4997. Min Act: -0.1700
Data Index: 1399719 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7185. Min Range: -5.7185
Max Act: 5.4997. Min Act: -0.1700
Data Index: 4491925 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7185. Min Range: -5.7185
Max Act: 5.4685. Min Act: -0.1700
Data Index: 1070771 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7185. Min Range: -5.7185
Max Act: 5.4685. Min Act: -0.1700
Data Index: 3057338 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #19