Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6209 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4433. Min Range: -8.4433
Max Act: 8.4433. Min Act: -0.1700
Data Index: 2867276 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4433. Min Range: -8.4433
Max Act: 8.3808. Min Act: -0.1700
Data Index: 5005846 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4433. Min Range: -8.4433
Max Act: 8.1308. Min Act: -0.1700
Data Index: 5043907 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4433. Min Range: -8.4433
Max Act: 8.0683. Min Act: -0.1700
Data Index: 691856 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4433. Min Range: -8.4433
Max Act: 8.0683. Min Act: -0.1700
Data Index: 1057870 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4433. Min Range: -8.4433
Max Act: 8.0683. Min Act: -0.1700
Data Index: 6569656 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4433. Min Range: -8.4433
Max Act: 8.0058. Min Act: -0.1700
Data Index: 1645916 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4433. Min Range: -8.4433
Max Act: 8.0058. Min Act: -0.1700
Data Index: 2407257 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4433. Min Range: -8.4433
Max Act: 8.0058. Min Act: -0.1700
Data Index: 5447843 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4433. Min Range: -8.4433
Max Act: 7.9433. Min Act: -0.1700
Data Index: 1258244 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4433. Min Range: -8.4433
Max Act: 7.9433. Min Act: -0.1700
Data Index: 4351675 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4433. Min Range: -8.4433
Max Act: 7.9433. Min Act: -0.1700
Data Index: 3846204 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4433. Min Range: -8.4433
Max Act: 7.9433. Min Act: -0.1700
Data Index: 5447842 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4433. Min Range: -8.4433
Max Act: 7.8808. Min Act: -0.1700
Data Index: 8298779 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4433. Min Range: -8.4433
Max Act: 7.9433. Min Act: -0.1700
Data Index: 7738224 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4433. Min Range: -8.4433
Max Act: 7.8808. Min Act: -0.1700
Data Index: 3710831 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4433. Min Range: -8.4433
Max Act: 7.8183. Min Act: -0.1700
Data Index: 232486 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4433. Min Range: -8.4433
Max Act: 7.8183. Min Act: -0.1700
Data Index: 2702336 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4433. Min Range: -8.4433
Max Act: 7.8183. Min Act: -0.1700
Data Index: 2988124 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4433. Min Range: -8.4433
Max Act: 7.8183. Min Act: -0.1700
Data Index: 6972457 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #19