Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3498 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6711. Min Range: -5.6711
Max Act: 5.6711. Min Act: -0.1700
Data Index: 7660756 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6711. Min Range: -5.6711
Max Act: 5.6711. Min Act: -0.1700
Data Index: 1993606 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6711. Min Range: -5.6711
Max Act: 5.5148. Min Act: -0.1700
Data Index: 3401732 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6711. Min Range: -5.6711
Max Act: 5.4836. Min Act: -0.1700
Data Index: 1027727 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6711. Min Range: -5.6711
Max Act: 5.4836. Min Act: -0.1700
Data Index: 7819424 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6711. Min Range: -5.6711
Max Act: 5.4523. Min Act: -0.1700
Data Index: 5220209 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6711. Min Range: -5.6711
Max Act: 5.4523. Min Act: -0.1700
Data Index: 728630 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6711. Min Range: -5.6711
Max Act: 5.4211. Min Act: -0.1700
Data Index: 5826348 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6711. Min Range: -5.6711
Max Act: 5.4211. Min Act: -0.1700
Data Index: 2695651 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6711. Min Range: -5.6711
Max Act: 5.4211. Min Act: -0.1700
Data Index: 7159452 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6711. Min Range: -5.6711
Max Act: 5.4211. Min Act: -0.1700
Data Index: 6201440 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6711. Min Range: -5.6711
Max Act: 5.3898. Min Act: -0.1700
Data Index: 8367932 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6711. Min Range: -5.6711
Max Act: 5.4211. Min Act: -0.1700
Data Index: 5170890 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6711. Min Range: -5.6711
Max Act: 5.3898. Min Act: -0.1700
Data Index: 3983392 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6711. Min Range: -5.6711
Max Act: 5.3586. Min Act: -0.1700
Data Index: 7299598 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6711. Min Range: -5.6711
Max Act: 5.3586. Min Act: -0.1700
Data Index: 571770 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6711. Min Range: -5.6711
Max Act: 5.3586. Min Act: -0.1700
Data Index: 4164359 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6711. Min Range: -5.6711
Max Act: 5.3273. Min Act: -0.1700
Data Index: 5826349 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6711. Min Range: -5.6711
Max Act: 5.3586. Min Act: -0.1700
Data Index: 8419619 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6711. Min Range: -5.6711
Max Act: 5.3586. Min Act: -0.1700
Data Index: 1547960 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #19