Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2747 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2336. Min Range: -6.2336
Max Act: 6.2336. Min Act: -0.1700
Data Index: 2539432 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2336. Min Range: -6.2336
Max Act: 6.1711. Min Act: -0.1700
Data Index: 7543811 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2336. Min Range: -6.2336
Max Act: 6.1399. Min Act: -0.1700
Data Index: 41319 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2336. Min Range: -6.2336
Max Act: 6.1399. Min Act: -0.1700
Data Index: 3396694 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2336. Min Range: -6.2336
Max Act: 6.1399. Min Act: -0.1700
Data Index: 39382 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2336. Min Range: -6.2336
Max Act: 6.1086. Min Act: -0.1700
Data Index: 1854809 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2336. Min Range: -6.2336
Max Act: 6.1086. Min Act: -0.1700
Data Index: 6108785 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2336. Min Range: -6.2336
Max Act: 6.1086. Min Act: -0.1700
Data Index: 1713559 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2336. Min Range: -6.2336
Max Act: 6.0774. Min Act: -0.1700
Data Index: 8036661 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2336. Min Range: -6.2336
Max Act: 6.0774. Min Act: -0.1700
Data Index: 5961905 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2336. Min Range: -6.2336
Max Act: 6.0774. Min Act: -0.1700
Data Index: 7858827 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2336. Min Range: -6.2336
Max Act: 6.0149. Min Act: -0.1700
Data Index: 7521770 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2336. Min Range: -6.2336
Max Act: 6.0461. Min Act: -0.1700
Data Index: 1044024 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2336. Min Range: -6.2336
Max Act: 6.0461. Min Act: -0.1700
Data Index: 1749800 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2336. Min Range: -6.2336
Max Act: 6.0149. Min Act: -0.1700
Data Index: 4774801 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2336. Min Range: -6.2336
Max Act: 6.0149. Min Act: -0.1700
Data Index: 5455763 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2336. Min Range: -6.2336
Max Act: 6.0149. Min Act: -0.1700
Data Index: 1142076 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2336. Min Range: -6.2336
Max Act: 5.9836. Min Act: -0.1700
Data Index: 5302890 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2336. Min Range: -6.2336
Max Act: 5.9836. Min Act: -0.1700
Data Index: 4930856 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2336. Min Range: -6.2336
Max Act: 5.9836. Min Act: -0.1700
Data Index: 4593687 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #19