Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3578 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0327. Min Range: -5.0327
Max Act: 5.0015. Min Act: -0.1700
Data Index: 4076584 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0327. Min Range: -5.0327
Max Act: 5.0327. Min Act: -0.1700
Data Index: 5742856 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0327. Min Range: -5.0327
Max Act: 5.0327. Min Act: -0.1700
Data Index: 2142841 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0327. Min Range: -5.0327
Max Act: 5.0015. Min Act: -0.1700
Data Index: 1900084 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0327. Min Range: -5.0327
Max Act: 5.0015. Min Act: -0.1700
Data Index: 1816566 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0327. Min Range: -5.0327
Max Act: 5.0015. Min Act: -0.1700
Data Index: 5161034 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0327. Min Range: -5.0327
Max Act: 4.9702. Min Act: -0.1700
Data Index: 6618956 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0327. Min Range: -5.0327
Max Act: 4.9390. Min Act: -0.1700
Data Index: 1601137 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0327. Min Range: -5.0327
Max Act: 4.9390. Min Act: -0.1700
Data Index: 5084831 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0327. Min Range: -5.0327
Max Act: 4.9077. Min Act: -0.1700
Data Index: 8350936 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0327. Min Range: -5.0327
Max Act: 4.8765. Min Act: -0.1700
Data Index: 4090623 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0327. Min Range: -5.0327
Max Act: 4.9077. Min Act: -0.1700
Data Index: 7755492 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0327. Min Range: -5.0327
Max Act: 4.8765. Min Act: -0.1700
Data Index: 2459240 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0327. Min Range: -5.0327
Max Act: 4.8452. Min Act: -0.1700
Data Index: 25691 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0327. Min Range: -5.0327
Max Act: 4.8452. Min Act: -0.1700
Data Index: 7547782 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0327. Min Range: -5.0327
Max Act: 4.8140. Min Act: -0.1700
Data Index: 1350559 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0327. Min Range: -5.0327
Max Act: 4.8140. Min Act: -0.1700
Data Index: 7171978 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0327. Min Range: -5.0327
Max Act: 4.7827. Min Act: -0.1700
Data Index: 4603608 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0327. Min Range: -5.0327
Max Act: 4.7515. Min Act: -0.1700
Data Index: 2553709 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0327. Min Range: -5.0327
Max Act: 4.7827. Min Act: -0.1700
Data Index: 109591 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #19