Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2752 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6746. Min Range: -10.6746
Max Act: 10.6746. Min Act: -0.1700
Data Index: 2690450 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6746. Min Range: -10.6746
Max Act: 9.8621. Min Act: -0.1700
Data Index: 8717523 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6746. Min Range: -10.6746
Max Act: 9.5496. Min Act: -0.1700
Data Index: 870232 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6746. Min Range: -10.6746
Max Act: 9.2996. Min Act: -0.1700
Data Index: 3660567 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6746. Min Range: -10.6746
Max Act: 9.1746. Min Act: -0.1700
Data Index: 8194054 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6746. Min Range: -10.6746
Max Act: 9.1121. Min Act: -0.1700
Data Index: 5489540 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6746. Min Range: -10.6746
Max Act: 9.1121. Min Act: -0.1700
Data Index: 7064561 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6746. Min Range: -10.6746
Max Act: 9.0496. Min Act: -0.1700
Data Index: 5133801 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6746. Min Range: -10.6746
Max Act: 9.0496. Min Act: -0.1700
Data Index: 4006025 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6746. Min Range: -10.6746
Max Act: 8.9871. Min Act: -0.1700
Data Index: 8022021 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6746. Min Range: -10.6746
Max Act: 8.9871. Min Act: -0.1700
Data Index: 5343322 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6746. Min Range: -10.6746
Max Act: 8.9871. Min Act: -0.1700
Data Index: 5603033 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6746. Min Range: -10.6746
Max Act: 8.9246. Min Act: -0.1700
Data Index: 4590857 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6746. Min Range: -10.6746
Max Act: 8.9246. Min Act: -0.1700
Data Index: 155688 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6746. Min Range: -10.6746
Max Act: 8.8621. Min Act: -0.1700
Data Index: 2861294 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6746. Min Range: -10.6746
Max Act: 8.8621. Min Act: -0.1700
Data Index: 4361987 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6746. Min Range: -10.6746
Max Act: 8.9246. Min Act: -0.1700
Data Index: 3960043 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6746. Min Range: -10.6746
Max Act: 8.7996. Min Act: -0.1700
Data Index: 8412954 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6746. Min Range: -10.6746
Max Act: 8.7996. Min Act: -0.1700
Data Index: 3812491 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6746. Min Range: -10.6746
Max Act: 8.7996. Min Act: -0.1700
Data Index: 3442266 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19