Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5518 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7589. Min Range: -8.7589
Max Act: 8.7589. Min Act: -0.1700
Data Index: 5758518 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7589. Min Range: -8.7589
Max Act: 8.5714. Min Act: -0.1700
Data Index: 801742 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7589. Min Range: -8.7589
Max Act: 8.5089. Min Act: -0.1700
Data Index: 1530576 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7589. Min Range: -8.7589
Max Act: 8.4464. Min Act: -0.1700
Data Index: 829077 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7589. Min Range: -8.7589
Max Act: 8.4464. Min Act: -0.1700
Data Index: 3504275 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7589. Min Range: -8.7589
Max Act: 8.3839. Min Act: -0.1700
Data Index: 3877958 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7589. Min Range: -8.7589
Max Act: 8.3214. Min Act: -0.1700
Data Index: 724081 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7589. Min Range: -8.7589
Max Act: 8.3214. Min Act: -0.1700
Data Index: 3956742 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7589. Min Range: -8.7589
Max Act: 8.3214. Min Act: -0.1700
Data Index: 182818 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7589. Min Range: -8.7589
Max Act: 8.1964. Min Act: -0.1700
Data Index: 5591487 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7589. Min Range: -8.7589
Max Act: 8.1964. Min Act: -0.1700
Data Index: 8378520 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7589. Min Range: -8.7589
Max Act: 8.1964. Min Act: -0.1700
Data Index: 241529 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7589. Min Range: -8.7589
Max Act: 8.1964. Min Act: -0.1700
Data Index: 4549567 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7589. Min Range: -8.7589
Max Act: 8.1964. Min Act: -0.1700
Data Index: 7266873 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7589. Min Range: -8.7589
Max Act: 8.1964. Min Act: -0.1700
Data Index: 347244 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7589. Min Range: -8.7589
Max Act: 8.1339. Min Act: -0.1700
Data Index: 1180748 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7589. Min Range: -8.7589
Max Act: 8.0714. Min Act: -0.1700
Data Index: 6314324 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7589. Min Range: -8.7589
Max Act: 8.1339. Min Act: -0.1700
Data Index: 5933332 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7589. Min Range: -8.7589
Max Act: 8.0714. Min Act: -0.1700
Data Index: 5613746 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7589. Min Range: -8.7589
Max Act: 8.0089. Min Act: -0.1700
Data Index: 7195069 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #19