Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2939 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4500. Min Range: -8.4500
Max Act: 8.4500. Min Act: -0.1700
Data Index: 3216944 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4500. Min Range: -8.4500
Max Act: 8.3250. Min Act: -0.1700
Data Index: 1192737 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4500. Min Range: -8.4500
Max Act: 8.2000. Min Act: -0.1700
Data Index: 8490370 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4500. Min Range: -8.4500
Max Act: 8.1375. Min Act: -0.1700
Data Index: 5378575 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4500. Min Range: -8.4500
Max Act: 8.1375. Min Act: -0.1700
Data Index: 2457601 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4500. Min Range: -8.4500
Max Act: 8.1063. Min Act: -0.1700
Data Index: 36484 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4500. Min Range: -8.4500
Max Act: 8.0438. Min Act: -0.1700
Data Index: 4711546 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4500. Min Range: -8.4500
Max Act: 8.0125. Min Act: -0.1700
Data Index: 1204145 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4500. Min Range: -8.4500
Max Act: 7.9813. Min Act: -0.1700
Data Index: 1204136 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4500. Min Range: -8.4500
Max Act: 7.9500. Min Act: -0.1700
Data Index: 2131250 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4500. Min Range: -8.4500
Max Act: 7.9500. Min Act: -0.1700
Data Index: 42262 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4500. Min Range: -8.4500
Max Act: 7.9188. Min Act: -0.1700
Data Index: 861114 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4500. Min Range: -8.4500
Max Act: 7.9188. Min Act: -0.1700
Data Index: 951125 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4500. Min Range: -8.4500
Max Act: 7.8875. Min Act: -0.1700
Data Index: 1819458 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4500. Min Range: -8.4500
Max Act: 7.8875. Min Act: -0.1700
Data Index: 4699561 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4500. Min Range: -8.4500
Max Act: 7.8563. Min Act: -0.1700
Data Index: 5188307 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4500. Min Range: -8.4500
Max Act: 7.8563. Min Act: -0.1700
Data Index: 5769254 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4500. Min Range: -8.4500
Max Act: 7.8250. Min Act: -0.1700
Data Index: 4696983 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4500. Min Range: -8.4500
Max Act: 7.7938. Min Act: -0.1700
Data Index: 7313875 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4500. Min Range: -8.4500
Max Act: 7.8563. Min Act: -0.1700
Data Index: 5027530 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #19