Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 841 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9144. Min Range: -7.9144
Max Act: 7.9144. Min Act: -0.1700
Data Index: 8328040 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9144. Min Range: -7.9144
Max Act: 7.6019. Min Act: -0.1700
Data Index: 8520600 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9144. Min Range: -7.9144
Max Act: 7.5394. Min Act: -0.1700
Data Index: 3471030 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9144. Min Range: -7.9144
Max Act: 7.5082. Min Act: -0.1700
Data Index: 5761259 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9144. Min Range: -7.9144
Max Act: 7.4769. Min Act: -0.1700
Data Index: 4833352 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9144. Min Range: -7.9144
Max Act: 7.3519. Min Act: -0.1700
Data Index: 7909955 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9144. Min Range: -7.9144
Max Act: 7.3519. Min Act: -0.1700
Data Index: 4006691 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9144. Min Range: -7.9144
Max Act: 7.2582. Min Act: -0.1700
Data Index: 1262730 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9144. Min Range: -7.9144
Max Act: 7.2582. Min Act: -0.1700
Data Index: 7364060 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9144. Min Range: -7.9144
Max Act: 7.2582. Min Act: -0.1700
Data Index: 5561148 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9144. Min Range: -7.9144
Max Act: 7.2269. Min Act: -0.1700
Data Index: 1903 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9144. Min Range: -7.9144
Max Act: 7.2269. Min Act: -0.1700
Data Index: 2723087 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9144. Min Range: -7.9144
Max Act: 7.1332. Min Act: -0.1700
Data Index: 4001717 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9144. Min Range: -7.9144
Max Act: 7.1957. Min Act: -0.1700
Data Index: 3178813 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9144. Min Range: -7.9144
Max Act: 7.1957. Min Act: -0.1700
Data Index: 3337893 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9144. Min Range: -7.9144
Max Act: 7.1644. Min Act: -0.1700
Data Index: 876788 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9144. Min Range: -7.9144
Max Act: 7.1644. Min Act: -0.1700
Data Index: 4536681 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9144. Min Range: -7.9144
Max Act: 7.1332. Min Act: -0.1700
Data Index: 5331495 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9144. Min Range: -7.9144
Max Act: 7.1644. Min Act: -0.1700
Data Index: 7022598 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9144. Min Range: -7.9144
Max Act: 7.1332. Min Act: -0.1700
Data Index: 5105868 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #19