Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3107 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6889. Min Range: -7.6889
Max Act: 7.6889. Min Act: -0.1700
Data Index: 8097759 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6889. Min Range: -7.6889
Max Act: 7.6889. Min Act: -0.1700
Data Index: 8463805 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6889. Min Range: -7.6889
Max Act: 7.6264. Min Act: -0.1700
Data Index: 5816930 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6889. Min Range: -7.6889
Max Act: 7.5639. Min Act: -0.1700
Data Index: 6180063 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6889. Min Range: -7.6889
Max Act: 7.5639. Min Act: -0.1700
Data Index: 3860605 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6889. Min Range: -7.6889
Max Act: 7.5014. Min Act: -0.1700
Data Index: 3154406 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6889. Min Range: -7.6889
Max Act: 7.5639. Min Act: -0.1698
Data Index: 4789304 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6889. Min Range: -7.6889
Max Act: 7.5639. Min Act: -0.1700
Data Index: 935140 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6889. Min Range: -7.6889
Max Act: 7.5014. Min Act: -0.1700
Data Index: 7128442 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6889. Min Range: -7.6889
Max Act: 7.5014. Min Act: -0.1700
Data Index: 3230604 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6889. Min Range: -7.6889
Max Act: 7.4389. Min Act: -0.1700
Data Index: 7060323 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6889. Min Range: -7.6889
Max Act: 7.4389. Min Act: -0.1700
Data Index: 1533280 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6889. Min Range: -7.6889
Max Act: 7.4389. Min Act: -0.1700
Data Index: 6770432 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6889. Min Range: -7.6889
Max Act: 7.4389. Min Act: -0.1700
Data Index: 3830975 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6889. Min Range: -7.6889
Max Act: 7.4389. Min Act: -0.1699
Data Index: 594837 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6889. Min Range: -7.6889
Max Act: 7.4389. Min Act: -0.1700
Data Index: 5889039 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6889. Min Range: -7.6889
Max Act: 7.3764. Min Act: -0.1700
Data Index: 7605209 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6889. Min Range: -7.6889
Max Act: 7.3764. Min Act: -0.1700
Data Index: 5686606 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6889. Min Range: -7.6889
Max Act: 7.3764. Min Act: -0.1700
Data Index: 1609871 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6889. Min Range: -7.6889
Max Act: 7.3451. Min Act: -0.1700
Data Index: 6229746 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #19