Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2340 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6638. Min Range: -4.6638
Max Act: 4.6638. Min Act: -0.1700
Data Index: 2181558 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6638. Min Range: -4.6638
Max Act: 4.6013. Min Act: -0.1700
Data Index: 1410606 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6638. Min Range: -4.6638
Max Act: 4.5701. Min Act: -0.1700
Data Index: 3630175 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6638. Min Range: -4.6638
Max Act: 4.5701. Min Act: -0.1700
Data Index: 159877 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6638. Min Range: -4.6638
Max Act: 4.5388. Min Act: -0.1700
Data Index: 3127556 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6638. Min Range: -4.6638
Max Act: 4.5388. Min Act: -0.1700
Data Index: 6586707 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6638. Min Range: -4.6638
Max Act: 4.5076. Min Act: -0.1700
Data Index: 6492537 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6638. Min Range: -4.6638
Max Act: 4.5701. Min Act: -0.1700
Data Index: 5061916 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6638. Min Range: -4.6638
Max Act: 4.5388. Min Act: -0.1700
Data Index: 5052146 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6638. Min Range: -4.6638
Max Act: 4.4763. Min Act: -0.1700
Data Index: 3638783 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6638. Min Range: -4.6638
Max Act: 4.5076. Min Act: -0.1700
Data Index: 7507530 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6638. Min Range: -4.6638
Max Act: 4.5076. Min Act: -0.1700
Data Index: 8424250 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6638. Min Range: -4.6638
Max Act: 4.4763. Min Act: -0.1700
Data Index: 8315197 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6638. Min Range: -4.6638
Max Act: 4.4763. Min Act: -0.1700
Data Index: 1579065 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6638. Min Range: -4.6638
Max Act: 4.4763. Min Act: -0.1700
Data Index: 4239955 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6638. Min Range: -4.6638
Max Act: 4.4763. Min Act: -0.1700
Data Index: 6188022 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6638. Min Range: -4.6638
Max Act: 4.4763. Min Act: -0.1700
Data Index: 6474744 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6638. Min Range: -4.6638
Max Act: 4.4763. Min Act: -0.1700
Data Index: 360707 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6638. Min Range: -4.6638
Max Act: 4.4763. Min Act: -0.1700
Data Index: 8728197 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6638. Min Range: -4.6638
Max Act: 4.4451. Min Act: -0.1700
Data Index: 6834580 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #19