Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4205 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0854. Min Range: -7.0854
Max Act: 7.0854. Min Act: -0.1700
Data Index: 5772276 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0854. Min Range: -7.0854
Max Act: 7.0229. Min Act: -0.1700
Data Index: 6924659 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0854. Min Range: -7.0854
Max Act: 6.8354. Min Act: -0.1700
Data Index: 5533529 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0854. Min Range: -7.0854
Max Act: 6.7729. Min Act: -0.1700
Data Index: 44737 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0854. Min Range: -7.0854
Max Act: 6.7104. Min Act: -0.1700
Data Index: 8325622 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0854. Min Range: -7.0854
Max Act: 6.7104. Min Act: -0.1700
Data Index: 1244807 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0854. Min Range: -7.0854
Max Act: 6.6792. Min Act: -0.1700
Data Index: 1540542 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0854. Min Range: -7.0854
Max Act: 6.6167. Min Act: -0.1700
Data Index: 7196455 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0854. Min Range: -7.0854
Max Act: 6.5542. Min Act: -0.1700
Data Index: 3926305 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0854. Min Range: -7.0854
Max Act: 6.5542. Min Act: -0.1700
Data Index: 217546 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0854. Min Range: -7.0854
Max Act: 6.5229. Min Act: -0.1700
Data Index: 7616665 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0854. Min Range: -7.0854
Max Act: 6.4917. Min Act: -0.1700
Data Index: 574350 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0854. Min Range: -7.0854
Max Act: 6.4604. Min Act: -0.1700
Data Index: 688100 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0854. Min Range: -7.0854
Max Act: 6.4604. Min Act: -0.1700
Data Index: 5561469 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0854. Min Range: -7.0854
Max Act: 6.4604. Min Act: -0.1700
Data Index: 1626115 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0854. Min Range: -7.0854
Max Act: 6.4292. Min Act: -0.1700
Data Index: 249827 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0854. Min Range: -7.0854
Max Act: 6.3979. Min Act: -0.1700
Data Index: 5853392 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0854. Min Range: -7.0854
Max Act: 6.3979. Min Act: -0.1700
Data Index: 8454078 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0854. Min Range: -7.0854
Max Act: 6.3979. Min Act: -0.1700
Data Index: 6511561 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0854. Min Range: -7.0854
Max Act: 6.3667. Min Act: -0.1700
Data Index: 3121627 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #19