Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3937 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2095. Min Range: -6.2095
Max Act: 6.2095. Min Act: -0.1700
Data Index: 6331083 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2095. Min Range: -6.2095
Max Act: 6.1158. Min Act: -0.1700
Data Index: 1942601 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2095. Min Range: -6.2095
Max Act: 6.0845. Min Act: -0.1700
Data Index: 3746980 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2095. Min Range: -6.2095
Max Act: 6.0845. Min Act: -0.1700
Data Index: 7806598 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2095. Min Range: -6.2095
Max Act: 6.0845. Min Act: -0.1700
Data Index: 7759038 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2095. Min Range: -6.2095
Max Act: 5.9595. Min Act: -0.1700
Data Index: 636373 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2095. Min Range: -6.2095
Max Act: 5.9595. Min Act: -0.1700
Data Index: 1735141 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2095. Min Range: -6.2095
Max Act: 5.9595. Min Act: -0.1700
Data Index: 5170016 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2095. Min Range: -6.2095
Max Act: 5.9283. Min Act: -0.1700
Data Index: 5484034 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2095. Min Range: -6.2095
Max Act: 5.9283. Min Act: -0.1700
Data Index: 6246716 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2095. Min Range: -6.2095
Max Act: 5.9595. Min Act: -0.1700
Data Index: 6246715 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2095. Min Range: -6.2095
Max Act: 5.8970. Min Act: -0.1700
Data Index: 3204011 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2095. Min Range: -6.2095
Max Act: 5.8970. Min Act: -0.1700
Data Index: 6234082 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2095. Min Range: -6.2095
Max Act: 5.8970. Min Act: -0.1700
Data Index: 4424305 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2095. Min Range: -6.2095
Max Act: 5.8970. Min Act: -0.1700
Data Index: 6327012 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2095. Min Range: -6.2095
Max Act: 5.8970. Min Act: -0.1700
Data Index: 4177567 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2095. Min Range: -6.2095
Max Act: 5.8658. Min Act: -0.1700
Data Index: 3238598 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2095. Min Range: -6.2095
Max Act: 5.8658. Min Act: -0.1700
Data Index: 4721092 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2095. Min Range: -6.2095
Max Act: 5.8345. Min Act: -0.1700
Data Index: 4828177 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2095. Min Range: -6.2095
Max Act: 5.8345. Min Act: -0.1700
Data Index: 2739366 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #19