Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3793 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1845. Min Range: -7.1845
Max Act: 7.1845. Min Act: -0.1700
Data Index: 5840196 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1845. Min Range: -7.1845
Max Act: 7.0908. Min Act: -0.1700
Data Index: 3667865 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1845. Min Range: -7.1845
Max Act: 7.0595. Min Act: -0.1700
Data Index: 7699998 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1845. Min Range: -7.1845
Max Act: 7.0283. Min Act: -0.1700
Data Index: 5948764 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1845. Min Range: -7.1845
Max Act: 6.9345. Min Act: -0.1700
Data Index: 4377099 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1845. Min Range: -7.1845
Max Act: 6.8720. Min Act: -0.1700
Data Index: 8558728 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1845. Min Range: -7.1845
Max Act: 6.9033. Min Act: -0.1700
Data Index: 2732722 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1845. Min Range: -7.1845
Max Act: 6.8095. Min Act: -0.1700
Data Index: 6295337 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1845. Min Range: -7.1845
Max Act: 6.8095. Min Act: -0.1700
Data Index: 3260189 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1845. Min Range: -7.1845
Max Act: 6.8095. Min Act: -0.1700
Data Index: 888769 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1845. Min Range: -7.1845
Max Act: 6.8095. Min Act: -0.1700
Data Index: 4513616 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1845. Min Range: -7.1845
Max Act: 6.7783. Min Act: -0.1700
Data Index: 1594251 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1845. Min Range: -7.1845
Max Act: 6.7470. Min Act: -0.1700
Data Index: 5767663 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1845. Min Range: -7.1845
Max Act: 6.7158. Min Act: -0.1700
Data Index: 7894000 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1845. Min Range: -7.1845
Max Act: 6.7470. Min Act: -0.1700
Data Index: 1429577 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1845. Min Range: -7.1845
Max Act: 6.6533. Min Act: -0.1700
Data Index: 6390454 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1845. Min Range: -7.1845
Max Act: 6.6845. Min Act: -0.1700
Data Index: 1893439 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1845. Min Range: -7.1845
Max Act: 6.6845. Min Act: -0.1700
Data Index: 3912866 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1845. Min Range: -7.1845
Max Act: 6.7158. Min Act: -0.1700
Data Index: 5932488 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1845. Min Range: -7.1845
Max Act: 6.6845. Min Act: -0.1700
Data Index: 957228 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #19