Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3598 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0352. Min Range: -8.0352
Max Act: 8.0352. Min Act: -0.1700
Data Index: 31060 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0352. Min Range: -8.0352
Max Act: 7.7852. Min Act: -0.1700
Data Index: 5052019 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0352. Min Range: -8.0352
Max Act: 7.5977. Min Act: -0.1700
Data Index: 6575260 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0352. Min Range: -8.0352
Max Act: 7.5040. Min Act: -0.1700
Data Index: 7043000 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0352. Min Range: -8.0352
Max Act: 7.5040. Min Act: -0.1700
Data Index: 8013106 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0352. Min Range: -8.0352
Max Act: 7.4415. Min Act: -0.1700
Data Index: 758851 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0352. Min Range: -8.0352
Max Act: 7.3790. Min Act: -0.1700
Data Index: 338640 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0352. Min Range: -8.0352
Max Act: 7.4102. Min Act: -0.1700
Data Index: 4427443 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0352. Min Range: -8.0352
Max Act: 7.3477. Min Act: -0.1700
Data Index: 1194114 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0352. Min Range: -8.0352
Max Act: 7.2852. Min Act: -0.1700
Data Index: 8299193 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0352. Min Range: -8.0352
Max Act: 7.2852. Min Act: -0.1700
Data Index: 5407276 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0352. Min Range: -8.0352
Max Act: 7.2852. Min Act: -0.1700
Data Index: 5963249 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0352. Min Range: -8.0352
Max Act: 7.1915. Min Act: -0.1700
Data Index: 6682548 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0352. Min Range: -8.0352
Max Act: 7.1602. Min Act: -0.1700
Data Index: 1694836 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0352. Min Range: -8.0352
Max Act: 7.1915. Min Act: -0.1700
Data Index: 1580685 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0352. Min Range: -8.0352
Max Act: 7.1602. Min Act: -0.1700
Data Index: 1872897 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0352. Min Range: -8.0352
Max Act: 7.1602. Min Act: -0.1700
Data Index: 8188190 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0352. Min Range: -8.0352
Max Act: 7.1602. Min Act: -0.1700
Data Index: 5196998 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0352. Min Range: -8.0352
Max Act: 7.1602. Min Act: -0.1700
Data Index: 251673 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0352. Min Range: -8.0352
Max Act: 7.0977. Min Act: -0.1700
Data Index: 7976585 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #19