Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6308 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1775. Min Range: -6.1775
Max Act: 6.1775. Min Act: -0.1700
Data Index: 599241 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1775. Min Range: -6.1775
Max Act: 6.1150. Min Act: -0.1700
Data Index: 3905001 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1775. Min Range: -6.1775
Max Act: 6.0838. Min Act: -0.1700
Data Index: 4361737 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1775. Min Range: -6.1775
Max Act: 6.0525. Min Act: -0.1700
Data Index: 7431469 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1775. Min Range: -6.1775
Max Act: 6.0213. Min Act: -0.1700
Data Index: 8700801 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1775. Min Range: -6.1775
Max Act: 5.9900. Min Act: -0.1700
Data Index: 3518573 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1775. Min Range: -6.1775
Max Act: 5.9900. Min Act: -0.1700
Data Index: 8286936 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1775. Min Range: -6.1775
Max Act: 5.9900. Min Act: -0.1700
Data Index: 3745159 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1775. Min Range: -6.1775
Max Act: 5.9588. Min Act: -0.1700
Data Index: 280936 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1775. Min Range: -6.1775
Max Act: 5.9588. Min Act: -0.1700
Data Index: 4181518 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1775. Min Range: -6.1775
Max Act: 5.9275. Min Act: -0.1700
Data Index: 5542882 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1775. Min Range: -6.1775
Max Act: 5.8963. Min Act: -0.1700
Data Index: 8780727 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1775. Min Range: -6.1775
Max Act: 5.8963. Min Act: -0.1700
Data Index: 464016 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1775. Min Range: -6.1775
Max Act: 5.8650. Min Act: -0.1700
Data Index: 7564673 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1775. Min Range: -6.1775
Max Act: 5.8650. Min Act: -0.1700
Data Index: 1511523 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1775. Min Range: -6.1775
Max Act: 5.8650. Min Act: -0.1700
Data Index: 178232 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1775. Min Range: -6.1775
Max Act: 5.8650. Min Act: -0.1700
Data Index: 7829940 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1775. Min Range: -6.1775
Max Act: 5.8025. Min Act: -0.1700
Data Index: 6700728 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1775. Min Range: -6.1775
Max Act: 5.7713. Min Act: -0.1700
Data Index: 4626124 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1775. Min Range: -6.1775
Max Act: 5.7713. Min Act: -0.1700
Data Index: 1078275 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19