Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4330 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1734. Min Range: -9.1734
Max Act: 9.1734. Min Act: -0.1700
Data Index: 4176490 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1734. Min Range: -9.1734
Max Act: 9.1734. Min Act: -0.1700
Data Index: 2643102 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1734. Min Range: -9.1734
Max Act: 9.1109. Min Act: -0.1700
Data Index: 7530615 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1734. Min Range: -9.1734
Max Act: 9.0484. Min Act: -0.1700
Data Index: 1429010 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1734. Min Range: -9.1734
Max Act: 8.9859. Min Act: -0.1700
Data Index: 7094639 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1734. Min Range: -9.1734
Max Act: 8.9859. Min Act: -0.1700
Data Index: 1410399 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1734. Min Range: -9.1734
Max Act: 8.9234. Min Act: -0.1700
Data Index: 8044793 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1734. Min Range: -9.1734
Max Act: 8.8609. Min Act: -0.1700
Data Index: 5274003 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1734. Min Range: -9.1734
Max Act: 8.8609. Min Act: -0.1700
Data Index: 3957650 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1734. Min Range: -9.1734
Max Act: 8.8609. Min Act: -0.1700
Data Index: 8799864 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1734. Min Range: -9.1734
Max Act: 8.8609. Min Act: -0.1700
Data Index: 8661246 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1734. Min Range: -9.1734
Max Act: 8.8609. Min Act: -0.1700
Data Index: 4095405 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1734. Min Range: -9.1734
Max Act: 8.8609. Min Act: -0.1700
Data Index: 6476299 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1734. Min Range: -9.1734
Max Act: 8.8609. Min Act: -0.1700
Data Index: 2008552 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1734. Min Range: -9.1734
Max Act: 8.8609. Min Act: -0.1700
Data Index: 5734339 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1734. Min Range: -9.1734
Max Act: 8.8609. Min Act: -0.1700
Data Index: 5481798 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1734. Min Range: -9.1734
Max Act: 8.7984. Min Act: -0.1698
Data Index: 4912895 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1734. Min Range: -9.1734
Max Act: 8.7984. Min Act: -0.1700
Data Index: 6661526 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1734. Min Range: -9.1734
Max Act: 8.7984. Min Act: -0.1700
Data Index: 281648 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1734. Min Range: -9.1734
Max Act: 8.7984. Min Act: -0.1700
Data Index: 2686028 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19