Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3422 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1227. Min Range: -4.1227
Max Act: 4.1227. Min Act: -0.1700
Data Index: 7124007 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1227. Min Range: -4.1227
Max Act: 3.9976. Min Act: -0.1700
Data Index: 4638876 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1227. Min Range: -4.1227
Max Act: 3.9976. Min Act: -0.1700
Data Index: 5741164 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1227. Min Range: -4.1227
Max Act: 3.9976. Min Act: -0.1700
Data Index: 458847 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1227. Min Range: -4.1227
Max Act: 3.8726. Min Act: -0.1700
Data Index: 7884269 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1227. Min Range: -4.1227
Max Act: 3.8413. Min Act: -0.1700
Data Index: 5619230 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1227. Min Range: -4.1227
Max Act: 3.7944. Min Act: -0.1700
Data Index: 2570291 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1227. Min Range: -4.1227
Max Act: 3.7788. Min Act: -0.1700
Data Index: 5085805 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1227. Min Range: -4.1227
Max Act: 3.7631. Min Act: -0.1700
Data Index: 6039554 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1227. Min Range: -4.1227
Max Act: 3.7631. Min Act: -0.1700
Data Index: 1896751 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1227. Min Range: -4.1227
Max Act: 3.7631. Min Act: -0.1700
Data Index: 616299 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1227. Min Range: -4.1227
Max Act: 3.7475. Min Act: -0.1700
Data Index: 7549209 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1227. Min Range: -4.1227
Max Act: 3.7475. Min Act: -0.1700
Data Index: 2399549 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1227. Min Range: -4.1227
Max Act: 3.7319. Min Act: -0.1700
Data Index: 6345959 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1227. Min Range: -4.1227
Max Act: 3.7319. Min Act: -0.1700
Data Index: 7304581 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1227. Min Range: -4.1227
Max Act: 3.6849. Min Act: -0.1700
Data Index: 2676727 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1227. Min Range: -4.1227
Max Act: 3.7006. Min Act: -0.1700
Data Index: 8271020 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1227. Min Range: -4.1227
Max Act: 3.7006. Min Act: -0.1700
Data Index: 533166 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1227. Min Range: -4.1227
Max Act: 3.6849. Min Act: -0.1700
Data Index: 3033648 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1227. Min Range: -4.1227
Max Act: 3.6849. Min Act: -0.1700
Data Index: 4830825 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #19