Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4560 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: 736155 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2095. Min Range: -6.2095
Max Act: 5.9907. Min Act: -0.1700
Data Index: 8728653 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2095. Min Range: -6.2095
Max Act: 5.9595. Min Act: -0.1700
Data Index: 3373702 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2095. Min Range: -6.2095
Max Act: 5.8970. Min Act: -0.1700
Data Index: 6807615 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2095. Min Range: -6.2095
Max Act: 5.8345. Min Act: -0.1700
Data Index: 6564937 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2095. Min Range: -6.2095
Max Act: 5.8657. Min Act: -0.1700
Data Index: 7826010 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2095. Min Range: -6.2095
Max Act: 5.8345. Min Act: -0.1700
Data Index: 6168530 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2095. Min Range: -6.2095
Max Act: 5.8032. Min Act: -0.1700
Data Index: 6513411 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2095. Min Range: -6.2095
Max Act: 5.7095. Min Act: -0.1700
Data Index: 3484379 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2095. Min Range: -6.2095
Max Act: 5.6782. Min Act: -0.1700
Data Index: 1920725 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2095. Min Range: -6.2095
Max Act: 5.6470. Min Act: -0.1700
Data Index: 898191 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2095. Min Range: -6.2095
Max Act: 5.6782. Min Act: -0.1700
Data Index: 4231174 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2095. Min Range: -6.2095
Max Act: 5.6470. Min Act: -0.1700
Data Index: 1710110 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2095. Min Range: -6.2095
Max Act: 5.6157. Min Act: -0.1700
Data Index: 1367433 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2095. Min Range: -6.2095
Max Act: 5.6157. Min Act: -0.1700
Data Index: 8750549 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2095. Min Range: -6.2095
Max Act: 5.5532. Min Act: -0.1700
Data Index: 7613889 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2095. Min Range: -6.2095
Max Act: 5.5845. Min Act: -0.1700
Data Index: 1024392 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2095. Min Range: -6.2095
Max Act: 5.5845. Min Act: -0.1700
Data Index: 498401 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2095. Min Range: -6.2095
Max Act: 5.5532. Min Act: -0.1700
Data Index: 5871280 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2095. Min Range: -6.2095
Max Act: 5.5220. Min Act: -0.1700
Data Index: 6227915 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #19