Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2003 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1648. Min Range: -3.1648
Max Act: 3.1648. Min Act: -0.1700
Data Index: 8014560 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1648. Min Range: -3.1648
Max Act: 3.0703. Min Act: -0.1700
Data Index: 1963737 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1648. Min Range: -3.1648
Max Act: 3.0545. Min Act: -0.1700
Data Index: 2958599 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1648. Min Range: -3.1648
Max Act: 3.0545. Min Act: -0.1700
Data Index: 3147566 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1648. Min Range: -3.1648
Max Act: 3.0545. Min Act: -0.1700
Data Index: 7214656 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1648. Min Range: -3.1648
Max Act: 3.0387. Min Act: -0.1700
Data Index: 6809740 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1648. Min Range: -3.1648
Max Act: 3.0387. Min Act: -0.1700
Data Index: 1131183 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1648. Min Range: -3.1648
Max Act: 3.0229. Min Act: -0.1700
Data Index: 124902 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1648. Min Range: -3.1648
Max Act: 3.0229. Min Act: -0.1700
Data Index: 5006141 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1648. Min Range: -3.1648
Max Act: 3.0229. Min Act: -0.1700
Data Index: 4028986 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1648. Min Range: -3.1648
Max Act: 3.0071. Min Act: -0.1700
Data Index: 4028985 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1648. Min Range: -3.1648
Max Act: 3.0071. Min Act: -0.1700
Data Index: 5673836 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1648. Min Range: -3.1648
Max Act: 3.0071. Min Act: -0.1700
Data Index: 8354351 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1648. Min Range: -3.1648
Max Act: 2.9913. Min Act: -0.1700
Data Index: 4441576 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1648. Min Range: -3.1648
Max Act: 2.9913. Min Act: -0.1700
Data Index: 3337571 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1648. Min Range: -3.1648
Max Act: 2.9913. Min Act: -0.1700
Data Index: 843890 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1648. Min Range: -3.1648
Max Act: 2.9913. Min Act: -0.1700
Data Index: 208048 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1648. Min Range: -3.1648
Max Act: 2.9913. Min Act: -0.1700
Data Index: 5435850 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1648. Min Range: -3.1648
Max Act: 2.9913. Min Act: -0.1700
Data Index: 7784200 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1648. Min Range: -3.1648
Max Act: 2.9913. Min Act: -0.1700
Data Index: 5725306 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #19