Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 647 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3739. Min Range: -4.3739
Max Act: 4.3739. Min Act: -0.1700
Data Index: 5787929 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3739. Min Range: -4.3739
Max Act: 4.2801. Min Act: -0.1700
Data Index: 8290230 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3739. Min Range: -4.3739
Max Act: 4.3114. Min Act: -0.1700
Data Index: 6645448 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3739. Min Range: -4.3739
Max Act: 4.1864. Min Act: -0.1700
Data Index: 4192865 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3739. Min Range: -4.3739
Max Act: 4.1864. Min Act: -0.1700
Data Index: 486625 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3739. Min Range: -4.3739
Max Act: 4.1551. Min Act: -0.1700
Data Index: 1390202 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3739. Min Range: -4.3739
Max Act: 4.1239. Min Act: -0.1700
Data Index: 858784 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3739. Min Range: -4.3739
Max Act: 4.1239. Min Act: -0.1700
Data Index: 6982853 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3739. Min Range: -4.3739
Max Act: 4.0926. Min Act: -0.1700
Data Index: 985674 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3739. Min Range: -4.3739
Max Act: 4.0926. Min Act: -0.1700
Data Index: 6645449 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3739. Min Range: -4.3739
Max Act: 4.0926. Min Act: -0.1700
Data Index: 7534073 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3739. Min Range: -4.3739
Max Act: 4.0301. Min Act: -0.1700
Data Index: 4968903 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3739. Min Range: -4.3739
Max Act: 4.0301. Min Act: -0.1700
Data Index: 6674356 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3739. Min Range: -4.3739
Max Act: 3.9988. Min Act: -0.1700
Data Index: 868188 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3739. Min Range: -4.3739
Max Act: 3.9988. Min Act: -0.1700
Data Index: 1046732 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3739. Min Range: -4.3739
Max Act: 4.0301. Min Act: -0.1700
Data Index: 7042496 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3739. Min Range: -4.3739
Max Act: 3.9988. Min Act: -0.1700
Data Index: 8452375 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3739. Min Range: -4.3739
Max Act: 3.9988. Min Act: -0.1700
Data Index: 8078793 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3739. Min Range: -4.3739
Max Act: 3.9988. Min Act: -0.1700
Data Index: 1092535 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3739. Min Range: -4.3739
Max Act: 3.9676. Min Act: -0.1700
Data Index: 3498635 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19