Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1533 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8497. Min Range: -6.8497
Max Act: 6.8497. Min Act: -0.1700
Data Index: 7597996 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8497. Min Range: -6.8497
Max Act: 6.8497. Min Act: -0.1700
Data Index: 3580019 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8497. Min Range: -6.8497
Max Act: 6.7247. Min Act: -0.1700
Data Index: 6500659 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8497. Min Range: -6.8497
Max Act: 6.7247. Min Act: -0.1700
Data Index: 6159077 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8497. Min Range: -6.8497
Max Act: 6.6622. Min Act: -0.1700
Data Index: 6500658 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8497. Min Range: -6.8497
Max Act: 6.6310. Min Act: -0.1700
Data Index: 4552451 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8497. Min Range: -6.8497
Max Act: 6.5997. Min Act: -0.1700
Data Index: 4190854 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8497. Min Range: -6.8497
Max Act: 6.5685. Min Act: -0.1700
Data Index: 6547860 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8497. Min Range: -6.8497
Max Act: 6.5372. Min Act: -0.1700
Data Index: 1779046 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8497. Min Range: -6.8497
Max Act: 6.5372. Min Act: -0.1700
Data Index: 7052893 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8497. Min Range: -6.8497
Max Act: 6.5372. Min Act: -0.1700
Data Index: 4002643 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8497. Min Range: -6.8497
Max Act: 6.5372. Min Act: -0.1700
Data Index: 4260860 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8497. Min Range: -6.8497
Max Act: 6.5372. Min Act: -0.1700
Data Index: 8474829 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8497. Min Range: -6.8497
Max Act: 6.5372. Min Act: -0.1700
Data Index: 2711687 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8497. Min Range: -6.8497
Max Act: 6.5060. Min Act: -0.1700
Data Index: 2901922 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8497. Min Range: -6.8497
Max Act: 6.5060. Min Act: -0.1700
Data Index: 6803439 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8497. Min Range: -6.8497
Max Act: 6.5060. Min Act: -0.1700
Data Index: 1113675 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8497. Min Range: -6.8497
Max Act: 6.5060. Min Act: -0.1700
Data Index: 5668024 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8497. Min Range: -6.8497
Max Act: 6.5060. Min Act: -0.1700
Data Index: 5131066 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8497. Min Range: -6.8497
Max Act: 6.5060. Min Act: -0.1700
Data Index: 8154804 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #19