Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1884 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3330. Min Range: -7.3330
Max Act: 7.3330. Min Act: -0.1700
Data Index: 3956231 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3330. Min Range: -7.3330
Max Act: 7.2705. Min Act: -0.1700
Data Index: 4430698 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3330. Min Range: -7.3330
Max Act: 7.1455. Min Act: -0.1700
Data Index: 5184682 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3330. Min Range: -7.3330
Max Act: 7.0830. Min Act: -0.1700
Data Index: 4592766 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3330. Min Range: -7.3330
Max Act: 7.0205. Min Act: -0.1700
Data Index: 4585046 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3330. Min Range: -7.3330
Max Act: 6.9893. Min Act: -0.1700
Data Index: 5550516 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3330. Min Range: -7.3330
Max Act: 6.9893. Min Act: -0.1700
Data Index: 4081940 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3330. Min Range: -7.3330
Max Act: 6.9580. Min Act: -0.1700
Data Index: 3985594 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3330. Min Range: -7.3330
Max Act: 6.9580. Min Act: -0.1700
Data Index: 3094039 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3330. Min Range: -7.3330
Max Act: 6.8955. Min Act: -0.1700
Data Index: 611631 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3330. Min Range: -7.3330
Max Act: 6.8955. Min Act: -0.1700
Data Index: 3643022 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3330. Min Range: -7.3330
Max Act: 6.9268. Min Act: -0.1700
Data Index: 6619188 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3330. Min Range: -7.3330
Max Act: 6.9268. Min Act: -0.1700
Data Index: 8456707 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3330. Min Range: -7.3330
Max Act: 6.8955. Min Act: -0.1700
Data Index: 4821211 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3330. Min Range: -7.3330
Max Act: 6.8955. Min Act: -0.1700
Data Index: 5764317 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3330. Min Range: -7.3330
Max Act: 6.8643. Min Act: -0.1700
Data Index: 982911 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3330. Min Range: -7.3330
Max Act: 6.8643. Min Act: -0.1700
Data Index: 8449975 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3330. Min Range: -7.3330
Max Act: 6.8330. Min Act: -0.1700
Data Index: 4001917 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3330. Min Range: -7.3330
Max Act: 6.8643. Min Act: -0.1700
Data Index: 7249520 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3330. Min Range: -7.3330
Max Act: 6.8018. Min Act: -0.1700
Data Index: 8157105 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #19