Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3654 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3351. Min Range: -8.3351
Max Act: 8.3351. Min Act: -0.1700
Data Index: 4983042 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3351. Min Range: -8.3351
Max Act: 8.0226. Min Act: -0.1700
Data Index: 4135787 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3351. Min Range: -8.3351
Max Act: 7.8351. Min Act: -0.1700
Data Index: 5344249 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3351. Min Range: -8.3351
Max Act: 7.8039. Min Act: -0.1700
Data Index: 3191585 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3351. Min Range: -8.3351
Max Act: 7.4601. Min Act: -0.1700
Data Index: 8007544 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3351. Min Range: -8.3351
Max Act: 7.4914. Min Act: -0.1700
Data Index: 8007543 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3351. Min Range: -8.3351
Max Act: 7.2101. Min Act: -0.1700
Data Index: 272193 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3351. Min Range: -8.3351
Max Act: 7.1789. Min Act: -0.1700
Data Index: 2673899 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3351. Min Range: -8.3351
Max Act: 7.1476. Min Act: -0.1700
Data Index: 1434272 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3351. Min Range: -8.3351
Max Act: 7.1476. Min Act: -0.1700
Data Index: 7255866 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3351. Min Range: -8.3351
Max Act: 7.0851. Min Act: -0.1700
Data Index: 3193097 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3351. Min Range: -8.3351
Max Act: 7.0539. Min Act: -0.1700
Data Index: 2725743 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3351. Min Range: -8.3351
Max Act: 7.0226. Min Act: -0.1700
Data Index: 2143173 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3351. Min Range: -8.3351
Max Act: 6.9601. Min Act: -0.1700
Data Index: 4553829 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3351. Min Range: -8.3351
Max Act: 6.8976. Min Act: -0.1700
Data Index: 4381437 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3351. Min Range: -8.3351
Max Act: 6.8976. Min Act: -0.1700
Data Index: 6023630 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3351. Min Range: -8.3351
Max Act: 6.8351. Min Act: -0.1700
Data Index: 3685636 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3351. Min Range: -8.3351
Max Act: 6.6789. Min Act: -0.1700
Data Index: 1136319 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3351. Min Range: -8.3351
Max Act: 6.6789. Min Act: -0.1700
Data Index: 7661681 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3351. Min Range: -8.3351
Max Act: 6.6164. Min Act: -0.1700
Data Index: 3820502 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #19