Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2839 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9891. Min Range: -2.9891
Max Act: 2.9891. Min Act: -0.1700
Data Index: 7544113 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9891. Min Range: -2.9891
Max Act: 2.9891. Min Act: -0.1700
Data Index: 3877898 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9891. Min Range: -2.9891
Max Act: 2.9733. Min Act: -0.1700
Data Index: 8032097 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9891. Min Range: -2.9891
Max Act: 2.9733. Min Act: -0.1700
Data Index: 6569168 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9891. Min Range: -2.9891
Max Act: 2.9575. Min Act: -0.1700
Data Index: 8288085 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9891. Min Range: -2.9891
Max Act: 2.9575. Min Act: -0.1700
Data Index: 3650745 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9891. Min Range: -2.9891
Max Act: 2.9575. Min Act: -0.1700
Data Index: 5493354 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9891. Min Range: -2.9891
Max Act: 2.9575. Min Act: -0.1700
Data Index: 1988671 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9891. Min Range: -2.9891
Max Act: 2.9575. Min Act: -0.1700
Data Index: 4765527 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9891. Min Range: -2.9891
Max Act: 2.9416. Min Act: -0.1700
Data Index: 1125913 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9891. Min Range: -2.9891
Max Act: 2.9416. Min Act: -0.1700
Data Index: 8274157 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9891. Min Range: -2.9891
Max Act: 2.9416. Min Act: -0.1700
Data Index: 3311899 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9891. Min Range: -2.9891
Max Act: 2.9416. Min Act: -0.1700
Data Index: 1141267 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9891. Min Range: -2.9891
Max Act: 2.9416. Min Act: -0.1700
Data Index: 1179801 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9891. Min Range: -2.9891
Max Act: 2.9416. Min Act: -0.1700
Data Index: 7825198 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9891. Min Range: -2.9891
Max Act: 2.9258. Min Act: -0.1700
Data Index: 2231147 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9891. Min Range: -2.9891
Max Act: 2.9258. Min Act: -0.1700
Data Index: 1706000 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9891. Min Range: -2.9891
Max Act: 2.9258. Min Act: -0.1700
Data Index: 3603638 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9891. Min Range: -2.9891
Max Act: 2.9258. Min Act: -0.1700
Data Index: 5766258 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9891. Min Range: -2.9891
Max Act: 2.9258. Min Act: -0.1700
Data Index: 6569155 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #19