Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3212 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5478. Min Range: -3.5478
Max Act: 3.5478. Min Act: -0.1700
Data Index: 7988606 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5478. Min Range: -3.5478
Max Act: 3.5321. Min Act: -0.1700
Data Index: 2864632 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5478. Min Range: -3.5478
Max Act: 3.5321. Min Act: -0.1700
Data Index: 7190347 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5478. Min Range: -3.5478
Max Act: 3.4538. Min Act: -0.1700
Data Index: 1984913 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5478. Min Range: -3.5478
Max Act: 3.4224. Min Act: -0.1700
Data Index: 59072 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5478. Min Range: -3.5478
Max Act: 3.4068. Min Act: -0.1700
Data Index: 1381626 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5478. Min Range: -3.5478
Max Act: 3.4068. Min Act: -0.1700
Data Index: 3371760 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5478. Min Range: -3.5478
Max Act: 3.4224. Min Act: -0.1700
Data Index: 3395588 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5478. Min Range: -3.5478
Max Act: 3.3911. Min Act: -0.1700
Data Index: 6940777 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5478. Min Range: -3.5478
Max Act: 3.3911. Min Act: -0.1700
Data Index: 7287918 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5478. Min Range: -3.5478
Max Act: 3.3754. Min Act: -0.1700
Data Index: 5318427 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5478. Min Range: -3.5478
Max Act: 3.3754. Min Act: -0.1700
Data Index: 3142164 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5478. Min Range: -3.5478
Max Act: 3.3754. Min Act: -0.1700
Data Index: 3263893 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5478. Min Range: -3.5478
Max Act: 3.3754. Min Act: -0.1700
Data Index: 2738338 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5478. Min Range: -3.5478
Max Act: 3.3597. Min Act: -0.1700
Data Index: 3907030 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5478. Min Range: -3.5478
Max Act: 3.3754. Min Act: -0.1700
Data Index: 4507482 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5478. Min Range: -3.5478
Max Act: 3.3597. Min Act: -0.1700
Data Index: 7159696 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5478. Min Range: -3.5478
Max Act: 3.3440. Min Act: -0.1700
Data Index: 1571225 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5478. Min Range: -3.5478
Max Act: 3.3440. Min Act: -0.1700
Data Index: 3889734 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5478. Min Range: -3.5478
Max Act: 3.3127. Min Act: -0.1700
Data Index: 2121093 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #19