Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1815 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.8259. Min Range: -10.8259
Max Act: 10.8259. Min Act: -0.1700
Data Index: 4658080 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8259. Min Range: -10.8259
Max Act: 10.7634. Min Act: -0.1700
Data Index: 1788553 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8259. Min Range: -10.8259
Max Act: 10.5759. Min Act: -0.1700
Data Index: 3570268 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8259. Min Range: -10.8259
Max Act: 10.4509. Min Act: -0.1700
Data Index: 1830066 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8259. Min Range: -10.8259
Max Act: 10.4509. Min Act: -0.1700
Data Index: 305578 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8259. Min Range: -10.8259
Max Act: 10.3259. Min Act: -0.1700
Data Index: 6867861 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8259. Min Range: -10.8259
Max Act: 10.3259. Min Act: -0.1700
Data Index: 7063574 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8259. Min Range: -10.8259
Max Act: 10.2634. Min Act: -0.1700
Data Index: 3916799 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8259. Min Range: -10.8259
Max Act: 10.2009. Min Act: -0.1700
Data Index: 2974643 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8259. Min Range: -10.8259
Max Act: 10.2009. Min Act: -0.1700
Data Index: 876602 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8259. Min Range: -10.8259
Max Act: 10.1384. Min Act: -0.1700
Data Index: 4413501 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8259. Min Range: -10.8259
Max Act: 10.0759. Min Act: -0.1700
Data Index: 200307 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8259. Min Range: -10.8259
Max Act: 10.0759. Min Act: -0.1700
Data Index: 2094836 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8259. Min Range: -10.8259
Max Act: 10.0759. Min Act: -0.1700
Data Index: 6923589 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8259. Min Range: -10.8259
Max Act: 10.0759. Min Act: -0.1700
Data Index: 654473 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8259. Min Range: -10.8259
Max Act: 10.0134. Min Act: -0.1700
Data Index: 4437000 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8259. Min Range: -10.8259
Max Act: 10.0134. Min Act: -0.1700
Data Index: 4728806 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8259. Min Range: -10.8259
Max Act: 10.0134. Min Act: -0.1700
Data Index: 7416979 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8259. Min Range: -10.8259
Max Act: 10.0134. Min Act: -0.1700
Data Index: 1697437 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8259. Min Range: -10.8259
Max Act: 10.0134. Min Act: -0.1700
Data Index: 7513129 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #19