Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6281 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0759. Min Range: -8.0759
Max Act: 8.0759. Min Act: -0.1700
Data Index: 1038509 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0759. Min Range: -8.0759
Max Act: 8.0759. Min Act: -0.1700
Data Index: 249264 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0759. Min Range: -8.0759
Max Act: 7.8884. Min Act: -0.1700
Data Index: 8266602 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0759. Min Range: -8.0759
Max Act: 7.8884. Min Act: -0.1700
Data Index: 2142325 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0759. Min Range: -8.0759
Max Act: 7.8884. Min Act: -0.1700
Data Index: 4159030 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0759. Min Range: -8.0759
Max Act: 7.8884. Min Act: -0.1700
Data Index: 7075219 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0759. Min Range: -8.0759
Max Act: 7.8884. Min Act: -0.1700
Data Index: 6098727 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0759. Min Range: -8.0759
Max Act: 7.8884. Min Act: -0.1700
Data Index: 1038506 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0759. Min Range: -8.0759
Max Act: 7.7634. Min Act: -0.1700
Data Index: 6606166 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0759. Min Range: -8.0759
Max Act: 7.7634. Min Act: -0.1700
Data Index: 1313697 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0759. Min Range: -8.0759
Max Act: 7.7634. Min Act: -0.1700
Data Index: 6143049 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0759. Min Range: -8.0759
Max Act: 7.7634. Min Act: -0.1700
Data Index: 3647337 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0759. Min Range: -8.0759
Max Act: 7.7634. Min Act: -0.1700
Data Index: 1038507 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0759. Min Range: -8.0759
Max Act: 7.7634. Min Act: -0.1700
Data Index: 4309252 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0759. Min Range: -8.0759
Max Act: 7.7634. Min Act: -0.1700
Data Index: 7265248 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0759. Min Range: -8.0759
Max Act: 7.7634. Min Act: -0.1700
Data Index: 2650100 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0759. Min Range: -8.0759
Max Act: 7.7009. Min Act: -0.1700
Data Index: 2170282 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0759. Min Range: -8.0759
Max Act: 7.7009. Min Act: -0.1700
Data Index: 3789814 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0759. Min Range: -8.0759
Max Act: 7.7009. Min Act: -0.1700
Data Index: 5725133 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0759. Min Range: -8.0759
Max Act: 7.7009. Min Act: -0.1700
Data Index: 3657376 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19