Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5306 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8020. Min Range: -7.8020
Max Act: 7.8020. Min Act: -0.1700
Data Index: 6884747 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8020. Min Range: -7.8020
Max Act: 7.7395. Min Act: -0.1700
Data Index: 2053098 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8020. Min Range: -7.8020
Max Act: 7.6770. Min Act: -0.1700
Data Index: 570099 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8020. Min Range: -7.8020
Max Act: 7.6458. Min Act: -0.1700
Data Index: 4127796 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8020. Min Range: -7.8020
Max Act: 7.6145. Min Act: -0.1700
Data Index: 2064070 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8020. Min Range: -7.8020
Max Act: 7.6458. Min Act: -0.1700
Data Index: 697671 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8020. Min Range: -7.8020
Max Act: 7.6145. Min Act: -0.1700
Data Index: 1094781 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8020. Min Range: -7.8020
Max Act: 7.6145. Min Act: -0.1700
Data Index: 2855687 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8020. Min Range: -7.8020
Max Act: 7.5833. Min Act: -0.1700
Data Index: 5743194 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8020. Min Range: -7.8020
Max Act: 7.5833. Min Act: -0.1700
Data Index: 6783592 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8020. Min Range: -7.8020
Max Act: 7.5520. Min Act: -0.1700
Data Index: 8353777 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8020. Min Range: -7.8020
Max Act: 7.5833. Min Act: -0.1700
Data Index: 7945197 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8020. Min Range: -7.8020
Max Act: 7.5520. Min Act: -0.1700
Data Index: 5062326 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8020. Min Range: -7.8020
Max Act: 7.5833. Min Act: -0.1700
Data Index: 234477 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8020. Min Range: -7.8020
Max Act: 7.5520. Min Act: -0.1700
Data Index: 1494739 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8020. Min Range: -7.8020
Max Act: 7.5833. Min Act: -0.1700
Data Index: 691782 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8020. Min Range: -7.8020
Max Act: 7.5208. Min Act: -0.1700
Data Index: 4019245 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8020. Min Range: -7.8020
Max Act: 7.4895. Min Act: -0.1700
Data Index: 5556974 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8020. Min Range: -7.8020
Max Act: 7.5208. Min Act: -0.1700
Data Index: 1720087 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8020. Min Range: -7.8020
Max Act: 7.4895. Min Act: -0.1700
Data Index: 6912640 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #19