Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2030 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8782. Min Range: -5.8782
Max Act: 5.8782. Min Act: -0.1700
Data Index: 5431884 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8782. Min Range: -5.8782
Max Act: 5.8782. Min Act: -0.1700
Data Index: 2680592 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8782. Min Range: -5.8782
Max Act: 5.8782. Min Act: -0.1700
Data Index: 5054294 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8782. Min Range: -5.8782
Max Act: 5.8157. Min Act: -0.1700
Data Index: 7851057 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8782. Min Range: -5.8782
Max Act: 5.8157. Min Act: -0.1700
Data Index: 1220254 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8782. Min Range: -5.8782
Max Act: 5.7532. Min Act: -0.1700
Data Index: 3716896 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8782. Min Range: -5.8782
Max Act: 5.7532. Min Act: -0.1700
Data Index: 5516544 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8782. Min Range: -5.8782
Max Act: 5.7532. Min Act: -0.1700
Data Index: 6440706 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8782. Min Range: -5.8782
Max Act: 5.7532. Min Act: -0.1700
Data Index: 6283882 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8782. Min Range: -5.8782
Max Act: 5.7532. Min Act: -0.1700
Data Index: 4168785 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8782. Min Range: -5.8782
Max Act: 5.7532. Min Act: -0.1700
Data Index: 4160306 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8782. Min Range: -5.8782
Max Act: 5.7532. Min Act: -0.1700
Data Index: 2200955 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8782. Min Range: -5.8782
Max Act: 5.7532. Min Act: -0.1700
Data Index: 5927746 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8782. Min Range: -5.8782
Max Act: 5.7219. Min Act: -0.1700
Data Index: 1116660 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8782. Min Range: -5.8782
Max Act: 5.7219. Min Act: -0.1700
Data Index: 3331333 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8782. Min Range: -5.8782
Max Act: 5.6907. Min Act: -0.1700
Data Index: 4786869 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8782. Min Range: -5.8782
Max Act: 5.6907. Min Act: -0.1700
Data Index: 5273941 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8782. Min Range: -5.8782
Max Act: 5.6907. Min Act: -0.1700
Data Index: 1171037 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8782. Min Range: -5.8782
Max Act: 5.6907. Min Act: -0.1700
Data Index: 841546 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8782. Min Range: -5.8782
Max Act: 5.6907. Min Act: -0.1700
Data Index: 8513368 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19