Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3777 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5600. Min Range: -10.5600
Max Act: 10.5600. Min Act: -0.1700
Data Index: 5219067 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5600. Min Range: -10.5600
Max Act: 10.0600. Min Act: -0.1700
Data Index: 4763539 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5600. Min Range: -10.5600
Max Act: 9.9350. Min Act: -0.1700
Data Index: 2603537 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5600. Min Range: -10.5600
Max Act: 9.9975. Min Act: -0.1700
Data Index: 922519 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5600. Min Range: -10.5600
Max Act: 9.9350. Min Act: -0.1700
Data Index: 3021827 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5600. Min Range: -10.5600
Max Act: 9.9350. Min Act: -0.1700
Data Index: 1573513 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5600. Min Range: -10.5600
Max Act: 9.9350. Min Act: -0.1700
Data Index: 3705321 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5600. Min Range: -10.5600
Max Act: 9.9350. Min Act: -0.1700
Data Index: 1567323 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5600. Min Range: -10.5600
Max Act: 9.8100. Min Act: -0.1700
Data Index: 3972864 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5600. Min Range: -10.5600
Max Act: 9.7475. Min Act: -0.1700
Data Index: 3440726 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5600. Min Range: -10.5600
Max Act: 9.7475. Min Act: -0.1700
Data Index: 6915713 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5600. Min Range: -10.5600
Max Act: 9.7475. Min Act: -0.1700
Data Index: 2209921 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5600. Min Range: -10.5600
Max Act: 9.6850. Min Act: -0.1700
Data Index: 4221194 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5600. Min Range: -10.5600
Max Act: 9.6225. Min Act: -0.1700
Data Index: 1594177 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5600. Min Range: -10.5600
Max Act: 9.6225. Min Act: -0.1700
Data Index: 4270142 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5600. Min Range: -10.5600
Max Act: 9.4975. Min Act: -0.1700
Data Index: 8636215 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5600. Min Range: -10.5600
Max Act: 9.4975. Min Act: -0.1700
Data Index: 7445438 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5600. Min Range: -10.5600
Max Act: 9.4975. Min Act: -0.1700
Data Index: 7852925 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5600. Min Range: -10.5600
Max Act: 9.4975. Min Act: -0.1700
Data Index: 3956401 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5600. Min Range: -10.5600
Max Act: 9.4350. Min Act: -0.1700
Data Index: 7655184 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #19