Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2833 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6821. Min Range: -5.6821
Max Act: 5.6821. Min Act: -0.1700
Data Index: 6871143 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6821. Min Range: -5.6821
Max Act: 5.4634. Min Act: -0.1700
Data Index: 7438030 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6821. Min Range: -5.6821
Max Act: 5.4634. Min Act: -0.1700
Data Index: 1043916 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6821. Min Range: -5.6821
Max Act: 5.4009. Min Act: -0.1700
Data Index: 1307651 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6821. Min Range: -5.6821
Max Act: 5.3071. Min Act: -0.1700
Data Index: 163117 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6821. Min Range: -5.6821
Max Act: 5.2759. Min Act: -0.1700
Data Index: 4831199 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6821. Min Range: -5.6821
Max Act: 5.2134. Min Act: -0.1700
Data Index: 7212733 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6821. Min Range: -5.6821
Max Act: 5.2446. Min Act: -0.1700
Data Index: 352673 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6821. Min Range: -5.6821
Max Act: 5.2134. Min Act: -0.1700
Data Index: 1694635 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6821. Min Range: -5.6821
Max Act: 5.1509. Min Act: -0.1700
Data Index: 4671170 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6821. Min Range: -5.6821
Max Act: 5.1821. Min Act: -0.1700
Data Index: 194594 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6821. Min Range: -5.6821
Max Act: 5.1509. Min Act: -0.1700
Data Index: 8730298 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6821. Min Range: -5.6821
Max Act: 5.1196. Min Act: -0.1700
Data Index: 5282295 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6821. Min Range: -5.6821
Max Act: 5.1509. Min Act: -0.1700
Data Index: 1980455 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6821. Min Range: -5.6821
Max Act: 5.1196. Min Act: -0.1700
Data Index: 1349409 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6821. Min Range: -5.6821
Max Act: 5.1509. Min Act: -0.1700
Data Index: 939213 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6821. Min Range: -5.6821
Max Act: 5.1196. Min Act: -0.1700
Data Index: 7662792 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6821. Min Range: -5.6821
Max Act: 5.0571. Min Act: -0.1700
Data Index: 4482574 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6821. Min Range: -5.6821
Max Act: 5.0884. Min Act: -0.1700
Data Index: 1743596 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6821. Min Range: -5.6821
Max Act: 5.0884. Min Act: -0.1700
Data Index: 6984982 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19