Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3309 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5590. Min Range: -4.5590
Max Act: 4.5590. Min Act: -0.1700
Data Index: 3020812 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5590. Min Range: -4.5590
Max Act: 4.5590. Min Act: -0.1700
Data Index: 4017928 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5590. Min Range: -4.5590
Max Act: 4.4028. Min Act: -0.1700
Data Index: 7999847 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5590. Min Range: -4.5590
Max Act: 4.3715. Min Act: -0.1700
Data Index: 1478848 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5590. Min Range: -4.5590
Max Act: 4.3715. Min Act: -0.1700
Data Index: 4011137 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5590. Min Range: -4.5590
Max Act: 4.3403. Min Act: -0.1700
Data Index: 3172125 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5590. Min Range: -4.5590
Max Act: 4.3403. Min Act: -0.1700
Data Index: 4078862 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5590. Min Range: -4.5590
Max Act: 4.3403. Min Act: -0.1700
Data Index: 3180848 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5590. Min Range: -4.5590
Max Act: 4.3090. Min Act: -0.1700
Data Index: 1704111 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5590. Min Range: -4.5590
Max Act: 4.3090. Min Act: -0.1700
Data Index: 756733 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5590. Min Range: -4.5590
Max Act: 4.3090. Min Act: -0.1700
Data Index: 8456723 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5590. Min Range: -4.5590
Max Act: 4.2465. Min Act: -0.1700
Data Index: 7720567 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5590. Min Range: -4.5590
Max Act: 4.2465. Min Act: -0.1700
Data Index: 8431226 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5590. Min Range: -4.5590
Max Act: 4.2153. Min Act: -0.1700
Data Index: 273675 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5590. Min Range: -4.5590
Max Act: 4.2153. Min Act: -0.1700
Data Index: 1869162 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5590. Min Range: -4.5590
Max Act: 4.2153. Min Act: -0.1700
Data Index: 6608948 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5590. Min Range: -4.5590
Max Act: 4.1840. Min Act: -0.1700
Data Index: 5692179 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5590. Min Range: -4.5590
Max Act: 4.1840. Min Act: -0.1700
Data Index: 1373223 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5590. Min Range: -4.5590
Max Act: 4.1840. Min Act: -0.1700
Data Index: 3171033 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5590. Min Range: -4.5590
Max Act: 4.1215. Min Act: -0.1700
Data Index: 8450025 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #19