Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 680 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9737. Min Range: -9.9737
Max Act: 9.9737. Min Act: -0.1700
Data Index: 4052254 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9737. Min Range: -9.9737
Max Act: 8.9737. Min Act: -0.1700
Data Index: 731631 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9737. Min Range: -9.9737
Max Act: 8.7862. Min Act: -0.1700
Data Index: 4981209 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9737. Min Range: -9.9737
Max Act: 8.7237. Min Act: -0.1700
Data Index: 8755632 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9737. Min Range: -9.9737
Max Act: 8.5987. Min Act: -0.1700
Data Index: 490425 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9737. Min Range: -9.9737
Max Act: 8.5362. Min Act: -0.1700
Data Index: 2325227 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9737. Min Range: -9.9737
Max Act: 8.5362. Min Act: -0.1700
Data Index: 922260 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9737. Min Range: -9.9737
Max Act: 8.5362. Min Act: -0.1700
Data Index: 1820821 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9737. Min Range: -9.9737
Max Act: 8.5362. Min Act: -0.1700
Data Index: 1948457 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9737. Min Range: -9.9737
Max Act: 8.4737. Min Act: -0.1700
Data Index: 6271823 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9737. Min Range: -9.9737
Max Act: 8.4737. Min Act: -0.1700
Data Index: 2151928 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9737. Min Range: -9.9737
Max Act: 8.4737. Min Act: -0.1700
Data Index: 255846 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9737. Min Range: -9.9737
Max Act: 8.4737. Min Act: -0.1700
Data Index: 6950150 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9737. Min Range: -9.9737
Max Act: 8.4737. Min Act: -0.1700
Data Index: 6538680 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9737. Min Range: -9.9737
Max Act: 8.4737. Min Act: -0.1700
Data Index: 255842 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9737. Min Range: -9.9737
Max Act: 8.4737. Min Act: -0.1700
Data Index: 5088887 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9737. Min Range: -9.9737
Max Act: 8.4737. Min Act: -0.1700
Data Index: 5725866 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9737. Min Range: -9.9737
Max Act: 8.4112. Min Act: -0.1700
Data Index: 738742 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9737. Min Range: -9.9737
Max Act: 8.4112. Min Act: -0.1700
Data Index: 3986049 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9737. Min Range: -9.9737
Max Act: 8.4112. Min Act: -0.1700
Data Index: 507921 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #19