Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3475 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6000. Min Range: -6.6000
Max Act: 6.6000. Min Act: -0.1700
Data Index: 3908124 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6000. Min Range: -6.6000
Max Act: 6.4125. Min Act: -0.1700
Data Index: 490344 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6000. Min Range: -6.6000
Max Act: 6.3813. Min Act: -0.1700
Data Index: 1905079 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6000. Min Range: -6.6000
Max Act: 6.2875. Min Act: -0.1700
Data Index: 1030276 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6000. Min Range: -6.6000
Max Act: 6.2250. Min Act: -0.1700
Data Index: 6566807 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6000. Min Range: -6.6000
Max Act: 6.2250. Min Act: -0.1700
Data Index: 3051606 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6000. Min Range: -6.6000
Max Act: 6.1313. Min Act: -0.1700
Data Index: 362561 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6000. Min Range: -6.6000
Max Act: 6.1313. Min Act: -0.1700
Data Index: 95530 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6000. Min Range: -6.6000
Max Act: 6.0688. Min Act: -0.1700
Data Index: 4345538 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6000. Min Range: -6.6000
Max Act: 6.1000. Min Act: -0.1700
Data Index: 6338532 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6000. Min Range: -6.6000
Max Act: 6.0688. Min Act: -0.1700
Data Index: 6230937 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6000. Min Range: -6.6000
Max Act: 6.0688. Min Act: -0.1700
Data Index: 4543995 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6000. Min Range: -6.6000
Max Act: 6.0688. Min Act: -0.1700
Data Index: 4287046 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6000. Min Range: -6.6000
Max Act: 6.0375. Min Act: -0.1700
Data Index: 6084153 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6000. Min Range: -6.6000
Max Act: 6.0375. Min Act: -0.1700
Data Index: 5933905 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6000. Min Range: -6.6000
Max Act: 6.0375. Min Act: -0.1700
Data Index: 3726165 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6000. Min Range: -6.6000
Max Act: 6.0063. Min Act: -0.1700
Data Index: 8667113 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6000. Min Range: -6.6000
Max Act: 5.9750. Min Act: -0.1700
Data Index: 3230055 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6000. Min Range: -6.6000
Max Act: 5.9750. Min Act: -0.1700
Data Index: 3628097 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6000. Min Range: -6.6000
Max Act: 5.9750. Min Act: -0.1700
Data Index: 3298137 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #19