Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3997 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0641. Min Range: -4.0641
Max Act: 4.0641. Min Act: -0.1700
Data Index: 2813844 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0641. Min Range: -4.0641
Max Act: 3.9703. Min Act: -0.1700
Data Index: 1446658 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0641. Min Range: -4.0641
Max Act: 3.9078. Min Act: -0.1700
Data Index: 2813845 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0641. Min Range: -4.0641
Max Act: 3.8922. Min Act: -0.1700
Data Index: 1773036 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0641. Min Range: -4.0641
Max Act: 3.7983. Min Act: -0.1700
Data Index: 1131184 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0641. Min Range: -4.0641
Max Act: 3.7827. Min Act: -0.1700
Data Index: 7926574 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0641. Min Range: -4.0641
Max Act: 3.7827. Min Act: -0.1700
Data Index: 2406802 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0641. Min Range: -4.0641
Max Act: 3.7671. Min Act: -0.1700
Data Index: 4214146 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0641. Min Range: -4.0641
Max Act: 3.7514. Min Act: -0.1700
Data Index: 6025418 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0641. Min Range: -4.0641
Max Act: 3.6889. Min Act: -0.1700
Data Index: 5861574 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0641. Min Range: -4.0641
Max Act: 3.6889. Min Act: -0.1700
Data Index: 479571 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0641. Min Range: -4.0641
Max Act: 3.6889. Min Act: -0.1700
Data Index: 7664542 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0641. Min Range: -4.0641
Max Act: 3.6889. Min Act: -0.1700
Data Index: 8509408 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0641. Min Range: -4.0641
Max Act: 3.6732. Min Act: -0.1700
Data Index: 5624492 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0641. Min Range: -4.0641
Max Act: 3.6732. Min Act: -0.1700
Data Index: 1791631 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0641. Min Range: -4.0641
Max Act: 3.6732. Min Act: -0.1700
Data Index: 302841 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0641. Min Range: -4.0641
Max Act: 3.6732. Min Act: -0.1700
Data Index: 2533511 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0641. Min Range: -4.0641
Max Act: 3.6889. Min Act: -0.1700
Data Index: 5751159 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0641. Min Range: -4.0641
Max Act: 3.6576. Min Act: -0.1700
Data Index: 4071287 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0641. Min Range: -4.0641
Max Act: 3.6576. Min Act: -0.1700
Data Index: 3984752 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19