Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2267 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5870. Min Range: -7.5870
Max Act: 7.5870. Min Act: -0.1700
Data Index: 6702343 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5870. Min Range: -7.5870
Max Act: 7.5245. Min Act: -0.1700
Data Index: 316854 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5870. Min Range: -7.5870
Max Act: 7.5558. Min Act: -0.1700
Data Index: 5613276 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5870. Min Range: -7.5870
Max Act: 7.4933. Min Act: -0.1700
Data Index: 3652252 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5870. Min Range: -7.5870
Max Act: 7.4933. Min Act: -0.1700
Data Index: 7933041 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5870. Min Range: -7.5870
Max Act: 7.4620. Min Act: -0.1700
Data Index: 5492864 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5870. Min Range: -7.5870
Max Act: 7.3995. Min Act: -0.1700
Data Index: 1856816 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5870. Min Range: -7.5870
Max Act: 7.3683. Min Act: -0.1700
Data Index: 5521168 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5870. Min Range: -7.5870
Max Act: 7.3370. Min Act: -0.1700
Data Index: 6146135 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5870. Min Range: -7.5870
Max Act: 7.3683. Min Act: -0.1700
Data Index: 6920145 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5870. Min Range: -7.5870
Max Act: 7.2745. Min Act: -0.1700
Data Index: 4349857 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5870. Min Range: -7.5870
Max Act: 7.2745. Min Act: -0.1700
Data Index: 7452888 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5870. Min Range: -7.5870
Max Act: 7.2745. Min Act: -0.1700
Data Index: 18562 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5870. Min Range: -7.5870
Max Act: 7.2433. Min Act: -0.1700
Data Index: 1629715 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5870. Min Range: -7.5870
Max Act: 7.1495. Min Act: -0.1700
Data Index: 1567482 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5870. Min Range: -7.5870
Max Act: 7.1808. Min Act: -0.1700
Data Index: 828358 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5870. Min Range: -7.5870
Max Act: 7.0870. Min Act: -0.1700
Data Index: 8662468 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5870. Min Range: -7.5870
Max Act: 7.1183. Min Act: -0.1700
Data Index: 6394964 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5870. Min Range: -7.5870
Max Act: 7.1183. Min Act: -0.1700
Data Index: 3899175 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5870. Min Range: -7.5870
Max Act: 7.0870. Min Act: -0.1700
Data Index: 6451508 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19