Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2631 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4432. Min Range: -9.4432
Max Act: 9.4432. Min Act: -0.1700
Data Index: 2893604 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4432. Min Range: -9.4432
Max Act: 9.4432. Min Act: -0.1700
Data Index: 3987602 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4432. Min Range: -9.4432
Max Act: 9.0682. Min Act: -0.1700
Data Index: 1526248 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4432. Min Range: -9.4432
Max Act: 9.0682. Min Act: -0.1700
Data Index: 3472433 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4432. Min Range: -9.4432
Max Act: 9.0057. Min Act: -0.1700
Data Index: 8618841 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4432. Min Range: -9.4432
Max Act: 8.8807. Min Act: -0.1700
Data Index: 8592607 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4432. Min Range: -9.4432
Max Act: 8.7557. Min Act: -0.1700
Data Index: 5355209 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4432. Min Range: -9.4432
Max Act: 8.8182. Min Act: -0.1700
Data Index: 2332498 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4432. Min Range: -9.4432
Max Act: 8.6307. Min Act: -0.1700
Data Index: 619810 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4432. Min Range: -9.4432
Max Act: 8.6932. Min Act: -0.1700
Data Index: 1169366 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4432. Min Range: -9.4432
Max Act: 8.6932. Min Act: -0.1700
Data Index: 782704 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4432. Min Range: -9.4432
Max Act: 8.6932. Min Act: -0.1700
Data Index: 3338738 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4432. Min Range: -9.4432
Max Act: 8.6307. Min Act: -0.1700
Data Index: 1228801 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4432. Min Range: -9.4432
Max Act: 8.6307. Min Act: -0.1700
Data Index: 1192545 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4432. Min Range: -9.4432
Max Act: 8.5682. Min Act: -0.1700
Data Index: 7073965 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4432. Min Range: -9.4432
Max Act: 8.5682. Min Act: -0.1700
Data Index: 3194610 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4432. Min Range: -9.4432
Max Act: 8.5057. Min Act: -0.1700
Data Index: 3774563 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4432. Min Range: -9.4432
Max Act: 8.4432. Min Act: -0.1700
Data Index: 1585716 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4432. Min Range: -9.4432
Max Act: 8.5057. Min Act: -0.1700
Data Index: 1888387 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4432. Min Range: -9.4432
Max Act: 8.5682. Min Act: -0.1700
Data Index: 463070 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #19