Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2623 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0685. Min Range: -6.0685
Max Act: 6.0685. Min Act: -0.1700
Data Index: 3688091 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0685. Min Range: -6.0685
Max Act: 5.9747. Min Act: -0.1700
Data Index: 2488678 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0685. Min Range: -6.0685
Max Act: 5.9435. Min Act: -0.1700
Data Index: 5346305 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0685. Min Range: -6.0685
Max Act: 5.8810. Min Act: -0.1700
Data Index: 4962868 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0685. Min Range: -6.0685
Max Act: 5.8497. Min Act: -0.1700
Data Index: 7601907 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0685. Min Range: -6.0685
Max Act: 5.8497. Min Act: -0.1700
Data Index: 6355651 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0685. Min Range: -6.0685
Max Act: 5.8185. Min Act: -0.1700
Data Index: 3977728 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0685. Min Range: -6.0685
Max Act: 5.7560. Min Act: -0.1700
Data Index: 7658969 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0685. Min Range: -6.0685
Max Act: 5.7560. Min Act: -0.1700
Data Index: 2693296 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0685. Min Range: -6.0685
Max Act: 5.7247. Min Act: -0.1700
Data Index: 952545 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0685. Min Range: -6.0685
Max Act: 5.6935. Min Act: -0.1700
Data Index: 717800 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0685. Min Range: -6.0685
Max Act: 5.6622. Min Act: -0.1700
Data Index: 5716740 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0685. Min Range: -6.0685
Max Act: 5.6622. Min Act: -0.1700
Data Index: 6495614 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0685. Min Range: -6.0685
Max Act: 5.6935. Min Act: -0.1700
Data Index: 2518456 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0685. Min Range: -6.0685
Max Act: 5.6622. Min Act: -0.1700
Data Index: 6295372 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0685. Min Range: -6.0685
Max Act: 5.6310. Min Act: -0.1700
Data Index: 3870558 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0685. Min Range: -6.0685
Max Act: 5.5997. Min Act: -0.1700
Data Index: 6916136 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0685. Min Range: -6.0685
Max Act: 5.5997. Min Act: -0.1700
Data Index: 4473166 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0685. Min Range: -6.0685
Max Act: 5.5685. Min Act: -0.1700
Data Index: 7440225 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0685. Min Range: -6.0685
Max Act: 5.5997. Min Act: -0.1700
Data Index: 2312068 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #19