Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 806 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8695. Min Range: -5.8695
Max Act: 5.8695. Min Act: -0.1700
Data Index: 3867872 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8695. Min Range: -5.8695
Max Act: 5.8695. Min Act: -0.1700
Data Index: 8250785 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8695. Min Range: -5.8695
Max Act: 5.6507. Min Act: -0.1700
Data Index: 8178135 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8695. Min Range: -5.8695
Max Act: 5.6195. Min Act: -0.1700
Data Index: 6120772 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8695. Min Range: -5.8695
Max Act: 5.5882. Min Act: -0.1700
Data Index: 5576818 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8695. Min Range: -5.8695
Max Act: 5.5570. Min Act: -0.1700
Data Index: 4862118 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8695. Min Range: -5.8695
Max Act: 5.5570. Min Act: -0.1700
Data Index: 1837744 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8695. Min Range: -5.8695
Max Act: 5.5257. Min Act: -0.1700
Data Index: 3193701 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8695. Min Range: -5.8695
Max Act: 5.4945. Min Act: -0.1700
Data Index: 8555838 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8695. Min Range: -5.8695
Max Act: 5.5570. Min Act: -0.1700
Data Index: 4414821 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8695. Min Range: -5.8695
Max Act: 5.5570. Min Act: -0.1700
Data Index: 3153316 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8695. Min Range: -5.8695
Max Act: 5.4945. Min Act: -0.1700
Data Index: 7130213 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8695. Min Range: -5.8695
Max Act: 5.4945. Min Act: -0.1700
Data Index: 892567 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8695. Min Range: -5.8695
Max Act: 5.4945. Min Act: -0.1700
Data Index: 6324919 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8695. Min Range: -5.8695
Max Act: 5.4632. Min Act: -0.1700
Data Index: 4558853 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8695. Min Range: -5.8695
Max Act: 5.4320. Min Act: -0.1700
Data Index: 3052661 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8695. Min Range: -5.8695
Max Act: 5.4007. Min Act: -0.1700
Data Index: 6036739 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8695. Min Range: -5.8695
Max Act: 5.4007. Min Act: -0.1700
Data Index: 8364239 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8695. Min Range: -5.8695
Max Act: 5.4320. Min Act: -0.1700
Data Index: 7375499 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8695. Min Range: -5.8695
Max Act: 5.4320. Min Act: -0.1700
Data Index: 285766 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #19