Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2099 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9696. Min Range: -9.9696
Max Act: 9.9696. Min Act: -0.1700
Data Index: 815441 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9696. Min Range: -9.9696
Max Act: 9.2821. Min Act: -0.1700
Data Index: 6235078 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9696. Min Range: -9.9696
Max Act: 9.2196. Min Act: -0.1700
Data Index: 4185970 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9696. Min Range: -9.9696
Max Act: 9.0946. Min Act: -0.1700
Data Index: 7083828 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9696. Min Range: -9.9696
Max Act: 9.0321. Min Act: -0.1700
Data Index: 5411583 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9696. Min Range: -9.9696
Max Act: 9.0321. Min Act: -0.1700
Data Index: 6641779 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9696. Min Range: -9.9696
Max Act: 8.9696. Min Act: -0.1700
Data Index: 1366506 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9696. Min Range: -9.9696
Max Act: 8.9696. Min Act: -0.1700
Data Index: 8688605 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9696. Min Range: -9.9696
Max Act: 8.8446. Min Act: -0.1700
Data Index: 273640 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9696. Min Range: -9.9696
Max Act: 8.8446. Min Act: -0.1700
Data Index: 6124867 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9696. Min Range: -9.9696
Max Act: 8.9071. Min Act: -0.1700
Data Index: 1079869 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9696. Min Range: -9.9696
Max Act: 8.7821. Min Act: -0.1700
Data Index: 5194155 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9696. Min Range: -9.9696
Max Act: 8.7821. Min Act: -0.1700
Data Index: 2310217 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9696. Min Range: -9.9696
Max Act: 8.7821. Min Act: -0.1700
Data Index: 3222054 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9696. Min Range: -9.9696
Max Act: 8.7821. Min Act: -0.1700
Data Index: 3006289 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9696. Min Range: -9.9696
Max Act: 8.7196. Min Act: -0.1700
Data Index: 8192332 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9696. Min Range: -9.9696
Max Act: 8.6571. Min Act: -0.1700
Data Index: 898760 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9696. Min Range: -9.9696
Max Act: 8.5946. Min Act: -0.1700
Data Index: 272545 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9696. Min Range: -9.9696
Max Act: 8.7196. Min Act: -0.1700
Data Index: 3195132 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9696. Min Range: -9.9696
Max Act: 8.5946. Min Act: -0.1700
Data Index: 4135738 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19