Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5896 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4679. Min Range: -6.4679
Max Act: 6.4679. Min Act: -0.1700
Data Index: 7904191 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4679. Min Range: -6.4679
Max Act: 6.4367. Min Act: -0.1700
Data Index: 3478919 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4679. Min Range: -6.4679
Max Act: 6.4054. Min Act: -0.1700
Data Index: 4175863 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4679. Min Range: -6.4679
Max Act: 6.3429. Min Act: -0.1700
Data Index: 3851713 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4679. Min Range: -6.4679
Max Act: 6.3429. Min Act: -0.1700
Data Index: 5977473 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4679. Min Range: -6.4679
Max Act: 6.3429. Min Act: -0.1700
Data Index: 8378760 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4679. Min Range: -6.4679
Max Act: 6.3117. Min Act: -0.1700
Data Index: 6950699 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4679. Min Range: -6.4679
Max Act: 6.2804. Min Act: -0.1700
Data Index: 8376811 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4679. Min Range: -6.4679
Max Act: 6.2804. Min Act: -0.1700
Data Index: 8822833 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4679. Min Range: -6.4679
Max Act: 6.2804. Min Act: -0.1700
Data Index: 4579862 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4679. Min Range: -6.4679
Max Act: 6.2804. Min Act: -0.1700
Data Index: 627678 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4679. Min Range: -6.4679
Max Act: 6.2804. Min Act: -0.1700
Data Index: 4873947 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4679. Min Range: -6.4679
Max Act: 6.2804. Min Act: -0.1700
Data Index: 6901346 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4679. Min Range: -6.4679
Max Act: 6.2804. Min Act: -0.1700
Data Index: 1130502 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4679. Min Range: -6.4679
Max Act: 6.2492. Min Act: -0.1700
Data Index: 3234996 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4679. Min Range: -6.4679
Max Act: 6.2804. Min Act: -0.1700
Data Index: 6365430 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4679. Min Range: -6.4679
Max Act: 6.2804. Min Act: -0.1700
Data Index: 6562523 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4679. Min Range: -6.4679
Max Act: 6.2492. Min Act: -0.1700
Data Index: 4586086 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4679. Min Range: -6.4679
Max Act: 6.2492. Min Act: -0.1700
Data Index: 2190177 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4679. Min Range: -6.4679
Max Act: 6.2179. Min Act: -0.1700
Data Index: 3436558 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19