Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1974 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9666. Min Range: -6.9666
Max Act: 6.9353. Min Act: -0.1700
Data Index: 4887933 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9666. Min Range: -6.9666
Max Act: 6.9666. Min Act: -0.1700
Data Index: 2193457 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9666. Min Range: -6.9666
Max Act: 6.8728. Min Act: -0.1700
Data Index: 5234336 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9666. Min Range: -6.9666
Max Act: 6.8103. Min Act: -0.1700
Data Index: 436737 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9666. Min Range: -6.9666
Max Act: 6.7478. Min Act: -0.1700
Data Index: 7534394 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9666. Min Range: -6.9666
Max Act: 6.7791. Min Act: -0.1700
Data Index: 6422956 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9666. Min Range: -6.9666
Max Act: 6.7791. Min Act: -0.1700
Data Index: 3282442 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9666. Min Range: -6.9666
Max Act: 6.6541. Min Act: -0.1700
Data Index: 4878796 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9666. Min Range: -6.9666
Max Act: 6.6541. Min Act: -0.1700
Data Index: 7466 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9666. Min Range: -6.9666
Max Act: 6.6541. Min Act: -0.1700
Data Index: 6816775 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9666. Min Range: -6.9666
Max Act: 6.5916. Min Act: -0.1700
Data Index: 2857825 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9666. Min Range: -6.9666
Max Act: 6.5291. Min Act: -0.1700
Data Index: 6067824 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9666. Min Range: -6.9666
Max Act: 6.5291. Min Act: -0.1700
Data Index: 2359035 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9666. Min Range: -6.9666
Max Act: 6.5603. Min Act: -0.1700
Data Index: 2705060 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9666. Min Range: -6.9666
Max Act: 6.4978. Min Act: -0.1700
Data Index: 686039 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9666. Min Range: -6.9666
Max Act: 6.4978. Min Act: -0.1700
Data Index: 4129045 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9666. Min Range: -6.9666
Max Act: 6.4978. Min Act: -0.1700
Data Index: 4217054 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9666. Min Range: -6.9666
Max Act: 6.4666. Min Act: -0.1700
Data Index: 2870514 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9666. Min Range: -6.9666
Max Act: 6.4666. Min Act: -0.1700
Data Index: 6067829 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9666. Min Range: -6.9666
Max Act: 6.4666. Min Act: -0.1700
Data Index: 5888331 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #19