Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4526 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0165. Min Range: -8.0165
Max Act: 8.0165. Min Act: -0.1700
Data Index: 1573769 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0165. Min Range: -8.0165
Max Act: 7.8915. Min Act: -0.1700
Data Index: 205541 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0165. Min Range: -8.0165
Max Act: 7.8915. Min Act: -0.1700
Data Index: 1336560 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0165. Min Range: -8.0165
Max Act: 7.7040. Min Act: -0.1700
Data Index: 2259646 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0165. Min Range: -8.0165
Max Act: 7.7040. Min Act: -0.1700
Data Index: 2578597 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0165. Min Range: -8.0165
Max Act: 7.6415. Min Act: -0.1700
Data Index: 1347170 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0165. Min Range: -8.0165
Max Act: 7.6415. Min Act: -0.1700
Data Index: 3812670 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0165. Min Range: -8.0165
Max Act: 7.5790. Min Act: -0.1700
Data Index: 7294156 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0165. Min Range: -8.0165
Max Act: 7.5790. Min Act: -0.1700
Data Index: 3143382 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0165. Min Range: -8.0165
Max Act: 7.5790. Min Act: -0.1700
Data Index: 2316989 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0165. Min Range: -8.0165
Max Act: 7.5790. Min Act: -0.1700
Data Index: 5860107 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0165. Min Range: -8.0165
Max Act: 7.5165. Min Act: -0.1700
Data Index: 280596 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0165. Min Range: -8.0165
Max Act: 7.5165. Min Act: -0.1700
Data Index: 6262302 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0165. Min Range: -8.0165
Max Act: 7.4852. Min Act: -0.1700
Data Index: 2288548 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0165. Min Range: -8.0165
Max Act: 7.4852. Min Act: -0.1700
Data Index: 4870056 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0165. Min Range: -8.0165
Max Act: 7.4852. Min Act: -0.1700
Data Index: 6942856 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0165. Min Range: -8.0165
Max Act: 7.4540. Min Act: -0.1700
Data Index: 3835474 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0165. Min Range: -8.0165
Max Act: 7.4227. Min Act: -0.1700
Data Index: 5388781 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0165. Min Range: -8.0165
Max Act: 7.3602. Min Act: -0.1700
Data Index: 1823826 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0165. Min Range: -8.0165
Max Act: 7.3915. Min Act: -0.1700
Data Index: 4675034 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #19