Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3438 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1564. Min Range: -7.1564
Max Act: 7.1564. Min Act: -0.1700
Data Index: 8651139 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1564. Min Range: -7.1564
Max Act: 7.0626. Min Act: -0.1700
Data Index: 180067 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1564. Min Range: -7.1564
Max Act: 6.8439. Min Act: -0.1700
Data Index: 267550 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1564. Min Range: -7.1564
Max Act: 6.8126. Min Act: -0.1700
Data Index: 6236940 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1564. Min Range: -7.1564
Max Act: 6.7501. Min Act: -0.1700
Data Index: 1747372 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1564. Min Range: -7.1564
Max Act: 6.7814. Min Act: -0.1700
Data Index: 5502041 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1564. Min Range: -7.1564
Max Act: 6.7189. Min Act: -0.1700
Data Index: 1235640 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1564. Min Range: -7.1564
Max Act: 6.6251. Min Act: -0.1700
Data Index: 3622188 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1564. Min Range: -7.1564
Max Act: 6.6251. Min Act: -0.1700
Data Index: 6356061 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1564. Min Range: -7.1564
Max Act: 6.6251. Min Act: -0.1700
Data Index: 2014831 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1564. Min Range: -7.1564
Max Act: 6.6251. Min Act: -0.1700
Data Index: 4720809 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1564. Min Range: -7.1564
Max Act: 6.5939. Min Act: -0.1700
Data Index: 2268475 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1564. Min Range: -7.1564
Max Act: 6.5939. Min Act: -0.1700
Data Index: 8808887 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1564. Min Range: -7.1564
Max Act: 6.5939. Min Act: -0.1700
Data Index: 3709282 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1564. Min Range: -7.1564
Max Act: 6.5939. Min Act: -0.1700
Data Index: 1407956 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1564. Min Range: -7.1564
Max Act: 6.5626. Min Act: -0.1700
Data Index: 8400091 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1564. Min Range: -7.1564
Max Act: 6.5626. Min Act: -0.1700
Data Index: 7305208 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1564. Min Range: -7.1564
Max Act: 6.5314. Min Act: -0.1700
Data Index: 3404869 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1564. Min Range: -7.1564
Max Act: 6.5314. Min Act: -0.1700
Data Index: 2210733 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1564. Min Range: -7.1564
Max Act: 6.5314. Min Act: -0.1700
Data Index: 4696068 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19