Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4608 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4752. Min Range: -5.4752
Max Act: 5.4752. Min Act: -0.1700
Data Index: 3507106 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4752. Min Range: -5.4752
Max Act: 5.3814. Min Act: -0.1700
Data Index: 7964719 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4752. Min Range: -5.4752
Max Act: 5.1627. Min Act: -0.1700
Data Index: 8793296 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4752. Min Range: -5.4752
Max Act: 5.1627. Min Act: -0.1700
Data Index: 5210404 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4752. Min Range: -5.4752
Max Act: 5.1002. Min Act: -0.1700
Data Index: 4635855 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4752. Min Range: -5.4752
Max Act: 4.9752. Min Act: -0.1700
Data Index: 642450 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4752. Min Range: -5.4752
Max Act: 4.9439. Min Act: -0.1700
Data Index: 7811800 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4752. Min Range: -5.4752
Max Act: 4.9439. Min Act: -0.1700
Data Index: 153638 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4752. Min Range: -5.4752
Max Act: 4.9752. Min Act: -0.1700
Data Index: 7327124 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4752. Min Range: -5.4752
Max Act: 4.8814. Min Act: -0.1700
Data Index: 296329 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4752. Min Range: -5.4752
Max Act: 4.8502. Min Act: -0.1700
Data Index: 5760620 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4752. Min Range: -5.4752
Max Act: 4.8502. Min Act: -0.1700
Data Index: 185844 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4752. Min Range: -5.4752
Max Act: 4.8502. Min Act: -0.1700
Data Index: 712931 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4752. Min Range: -5.4752
Max Act: 4.8189. Min Act: -0.1700
Data Index: 4440979 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4752. Min Range: -5.4752
Max Act: 4.8189. Min Act: -0.1700
Data Index: 8001883 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4752. Min Range: -5.4752
Max Act: 4.7877. Min Act: -0.1700
Data Index: 6651384 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4752. Min Range: -5.4752
Max Act: 4.7564. Min Act: -0.1700
Data Index: 2578036 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4752. Min Range: -5.4752
Max Act: 4.7877. Min Act: -0.1700
Data Index: 7353147 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4752. Min Range: -5.4752
Max Act: 4.7564. Min Act: -0.1700
Data Index: 1958044 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4752. Min Range: -5.4752
Max Act: 4.7252. Min Act: -0.1700
Data Index: 4738704 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #19