Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3036 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9978. Min Range: -6.9978
Max Act: 6.9978. Min Act: -0.1700
Data Index: 2981266 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9978. Min Range: -6.9978
Max Act: 6.8103. Min Act: -0.1700
Data Index: 1509906 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9978. Min Range: -6.9978
Max Act: 6.7791. Min Act: -0.1700
Data Index: 5379918 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9978. Min Range: -6.9978
Max Act: 6.6541. Min Act: -0.1700
Data Index: 1743005 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9978. Min Range: -6.9978
Max Act: 6.6541. Min Act: -0.1700
Data Index: 8027191 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9978. Min Range: -6.9978
Max Act: 6.6541. Min Act: -0.1700
Data Index: 123097 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9978. Min Range: -6.9978
Max Act: 6.5916. Min Act: -0.1700
Data Index: 2524585 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9978. Min Range: -6.9978
Max Act: 6.5916. Min Act: -0.1700
Data Index: 8635493 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9978. Min Range: -6.9978
Max Act: 6.5916. Min Act: -0.1700
Data Index: 4672234 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9978. Min Range: -6.9978
Max Act: 6.4978. Min Act: -0.1700
Data Index: 4646749 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9978. Min Range: -6.9978
Max Act: 6.4978. Min Act: -0.1700
Data Index: 6833245 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9978. Min Range: -6.9978
Max Act: 6.4666. Min Act: -0.1700
Data Index: 4616406 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9978. Min Range: -6.9978
Max Act: 6.4978. Min Act: -0.1700
Data Index: 2317521 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9978. Min Range: -6.9978
Max Act: 6.4353. Min Act: -0.1700
Data Index: 3211093 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9978. Min Range: -6.9978
Max Act: 6.4353. Min Act: -0.1700
Data Index: 2913330 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9978. Min Range: -6.9978
Max Act: 6.4353. Min Act: -0.1700
Data Index: 6614557 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9978. Min Range: -6.9978
Max Act: 6.4353. Min Act: -0.1700
Data Index: 7966866 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9978. Min Range: -6.9978
Max Act: 6.4353. Min Act: -0.1700
Data Index: 6572568 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9978. Min Range: -6.9978
Max Act: 6.4353. Min Act: -0.1700
Data Index: 1679333 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9978. Min Range: -6.9978
Max Act: 6.4353. Min Act: -0.1700
Data Index: 3148337 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #19