Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4649 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8130. Min Range: -2.8130
Max Act: 2.8130. Min Act: -0.1700
Data Index: 4083835 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8130. Min Range: -2.8130
Max Act: 2.7493. Min Act: -0.1700
Data Index: 5221594 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8130. Min Range: -2.8130
Max Act: 2.7013. Min Act: -0.1700
Data Index: 4195965 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8130. Min Range: -2.8130
Max Act: 2.6693. Min Act: -0.1700
Data Index: 946114 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8130. Min Range: -2.8130
Max Act: 2.6372. Min Act: -0.1700
Data Index: 5425503 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8130. Min Range: -2.8130
Max Act: 2.6372. Min Act: -0.1700
Data Index: 2366856 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8130. Min Range: -2.8130
Max Act: 2.6211. Min Act: -0.1700
Data Index: 2268579 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8130. Min Range: -2.8130
Max Act: 2.6051. Min Act: -0.1700
Data Index: 3475443 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8130. Min Range: -2.8130
Max Act: 2.6051. Min Act: -0.1700
Data Index: 3650026 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8130. Min Range: -2.8130
Max Act: 2.6051. Min Act: -0.1700
Data Index: 5911570 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8130. Min Range: -2.8130
Max Act: 2.5890. Min Act: -0.1700
Data Index: 7726816 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8130. Min Range: -2.8130
Max Act: 2.5890. Min Act: -0.1700
Data Index: 3604349 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8130. Min Range: -2.8130
Max Act: 2.6051. Min Act: -0.1700
Data Index: 1683997 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8130. Min Range: -2.8130
Max Act: 2.6051. Min Act: -0.1700
Data Index: 5740768 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8130. Min Range: -2.8130
Max Act: 2.5890. Min Act: -0.1700
Data Index: 4300208 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8130. Min Range: -2.8130
Max Act: 2.5728. Min Act: -0.1700
Data Index: 1099291 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8130. Min Range: -2.8130
Max Act: 2.5728. Min Act: -0.1700
Data Index: 8830677 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8130. Min Range: -2.8130
Max Act: 2.5406. Min Act: -0.1700
Data Index: 6783700 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8130. Min Range: -2.8130
Max Act: 2.5567. Min Act: -0.1700
Data Index: 5379326 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8130. Min Range: -2.8130
Max Act: 2.5567. Min Act: -0.1700
Data Index: 1537308 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19