Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4665 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.2166. Min Range: -11.2166
Max Act: 11.2166. Min Act: -0.1700
Data Index: 897518 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.2166. Min Range: -11.2166
Max Act: 10.6541. Min Act: -0.1700
Data Index: 8385424 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.2166. Min Range: -11.2166
Max Act: 10.5916. Min Act: -0.1700
Data Index: 1626681 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.2166. Min Range: -11.2166
Max Act: 10.5291. Min Act: -0.1700
Data Index: 6355492 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.2166. Min Range: -11.2166
Max Act: 10.4041. Min Act: -0.1700
Data Index: 1939653 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.2166. Min Range: -11.2166
Max Act: 10.2166. Min Act: -0.1700
Data Index: 5652180 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.2166. Min Range: -11.2166
Max Act: 10.2166. Min Act: -0.1700
Data Index: 8317725 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.2166. Min Range: -11.2166
Max Act: 10.2791. Min Act: -0.1700
Data Index: 1974563 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.2166. Min Range: -11.2166
Max Act: 10.1541. Min Act: -0.1700
Data Index: 1626680 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.2166. Min Range: -11.2166
Max Act: 10.0916. Min Act: -0.1700
Data Index: 4394634 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.2166. Min Range: -11.2166
Max Act: 10.0916. Min Act: -0.1700
Data Index: 1471638 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.2166. Min Range: -11.2166
Max Act: 10.0916. Min Act: -0.1700
Data Index: 946135 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.2166. Min Range: -11.2166
Max Act: 10.0291. Min Act: -0.1700
Data Index: 6644500 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.2166. Min Range: -11.2166
Max Act: 10.0291. Min Act: -0.1700
Data Index: 4042807 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.2166. Min Range: -11.2166
Max Act: 10.0291. Min Act: -0.1700
Data Index: 1424471 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.2166. Min Range: -11.2166
Max Act: 10.0291. Min Act: -0.1700
Data Index: 6355480 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.2166. Min Range: -11.2166
Max Act: 10.0291. Min Act: -0.1700
Data Index: 656544 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.2166. Min Range: -11.2166
Max Act: 10.0291. Min Act: -0.1700
Data Index: 5713891 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.2166. Min Range: -11.2166
Max Act: 10.0291. Min Act: -0.1700
Data Index: 1794255 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.2166. Min Range: -11.2166
Max Act: 9.9666. Min Act: -0.1700
Data Index: 6791718 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #19