Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1977 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1831. Min Range: -6.1831
Max Act: 6.1831. Min Act: -0.1700
Data Index: 4298498 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1831. Min Range: -6.1831
Max Act: 6.1206. Min Act: -0.1700
Data Index: 7436825 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1831. Min Range: -6.1831
Max Act: 6.0268. Min Act: -0.1700
Data Index: 1602134 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1831. Min Range: -6.1831
Max Act: 6.0268. Min Act: -0.1700
Data Index: 485388 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1831. Min Range: -6.1831
Max Act: 6.0268. Min Act: -0.1700
Data Index: 1002234 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1831. Min Range: -6.1831
Max Act: 5.9956. Min Act: -0.1700
Data Index: 8554887 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1831. Min Range: -6.1831
Max Act: 5.9956. Min Act: -0.1700
Data Index: 3402884 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1831. Min Range: -6.1831
Max Act: 5.9331. Min Act: -0.1700
Data Index: 2840052 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1831. Min Range: -6.1831
Max Act: 5.9331. Min Act: -0.1700
Data Index: 1577018 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1831. Min Range: -6.1831
Max Act: 5.9331. Min Act: -0.1700
Data Index: 225311 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1831. Min Range: -6.1831
Max Act: 5.8706. Min Act: -0.1700
Data Index: 4518171 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1831. Min Range: -6.1831
Max Act: 5.9018. Min Act: -0.1700
Data Index: 7933921 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1831. Min Range: -6.1831
Max Act: 5.9018. Min Act: -0.1700
Data Index: 7389788 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1831. Min Range: -6.1831
Max Act: 5.9018. Min Act: -0.1700
Data Index: 6908416 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1831. Min Range: -6.1831
Max Act: 5.9018. Min Act: -0.1700
Data Index: 4581424 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1831. Min Range: -6.1831
Max Act: 5.9018. Min Act: -0.1700
Data Index: 2145030 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1831. Min Range: -6.1831
Max Act: 5.9018. Min Act: -0.1700
Data Index: 1435468 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1831. Min Range: -6.1831
Max Act: 5.8706. Min Act: -0.1700
Data Index: 390858 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1831. Min Range: -6.1831
Max Act: 5.8706. Min Act: -0.1700
Data Index: 1710322 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1831. Min Range: -6.1831
Max Act: 5.8706. Min Act: -0.1700
Data Index: 3226309 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19