Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2737 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1773. Min Range: -6.1773
Max Act: 6.1773. Min Act: -0.1700
Data Index: 7904981 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1773. Min Range: -6.1773
Max Act: 6.1460. Min Act: -0.1700
Data Index: 7619974 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1773. Min Range: -6.1773
Max Act: 6.0835. Min Act: -0.1700
Data Index: 3761229 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1773. Min Range: -6.1773
Max Act: 6.0835. Min Act: -0.1700
Data Index: 8831903 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1773. Min Range: -6.1773
Max Act: 6.0523. Min Act: -0.1700
Data Index: 6693630 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1773. Min Range: -6.1773
Max Act: 5.9585. Min Act: -0.1700
Data Index: 5472087 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1773. Min Range: -6.1773
Max Act: 5.9898. Min Act: -0.1700
Data Index: 7640248 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1773. Min Range: -6.1773
Max Act: 5.9898. Min Act: -0.1700
Data Index: 5653447 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1773. Min Range: -6.1773
Max Act: 6.0210. Min Act: -0.1700
Data Index: 1026773 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1773. Min Range: -6.1773
Max Act: 5.9585. Min Act: -0.1700
Data Index: 1649492 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1773. Min Range: -6.1773
Max Act: 5.9585. Min Act: -0.1700
Data Index: 3715354 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1773. Min Range: -6.1773
Max Act: 5.9273. Min Act: -0.1700
Data Index: 7472784 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1773. Min Range: -6.1773
Max Act: 5.9273. Min Act: -0.1700
Data Index: 6557612 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1773. Min Range: -6.1773
Max Act: 5.9273. Min Act: -0.1700
Data Index: 2963098 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1773. Min Range: -6.1773
Max Act: 5.8960. Min Act: -0.1700
Data Index: 5988806 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1773. Min Range: -6.1773
Max Act: 5.8960. Min Act: -0.1700
Data Index: 5329465 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1773. Min Range: -6.1773
Max Act: 5.8960. Min Act: -0.1700
Data Index: 8546193 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1773. Min Range: -6.1773
Max Act: 5.8648. Min Act: -0.1700
Data Index: 5723053 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1773. Min Range: -6.1773
Max Act: 5.8648. Min Act: -0.1700
Data Index: 4520918 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1773. Min Range: -6.1773
Max Act: 5.8335. Min Act: -0.1700
Data Index: 1984736 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #19