Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3415 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4112. Min Range: -8.4112
Max Act: 8.4112. Min Act: -0.1700
Data Index: 7067866 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4112. Min Range: -8.4112
Max Act: 8.2237. Min Act: -0.1700
Data Index: 1504008 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4112. Min Range: -8.4112
Max Act: 8.0987. Min Act: -0.1700
Data Index: 7067862 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4112. Min Range: -8.4112
Max Act: 8.0987. Min Act: -0.1700
Data Index: 6954596 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4112. Min Range: -8.4112
Max Act: 8.0362. Min Act: -0.1700
Data Index: 8782379 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4112. Min Range: -8.4112
Max Act: 8.0362. Min Act: -0.1700
Data Index: 4652721 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4112. Min Range: -8.4112
Max Act: 7.9737. Min Act: -0.1700
Data Index: 3430240 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4112. Min Range: -8.4112
Max Act: 7.9737. Min Act: -0.1700
Data Index: 7067865 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4112. Min Range: -8.4112
Max Act: 7.9112. Min Act: -0.1700
Data Index: 8824499 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4112. Min Range: -8.4112
Max Act: 7.9112. Min Act: -0.1700
Data Index: 4913803 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4112. Min Range: -8.4112
Max Act: 7.8487. Min Act: -0.1700
Data Index: 4173039 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4112. Min Range: -8.4112
Max Act: 7.8487. Min Act: -0.1700
Data Index: 6557474 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4112. Min Range: -8.4112
Max Act: 7.8487. Min Act: -0.1700
Data Index: 4913802 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4112. Min Range: -8.4112
Max Act: 7.8487. Min Act: -0.1700
Data Index: 5756148 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4112. Min Range: -8.4112
Max Act: 7.7862. Min Act: -0.1700
Data Index: 7067864 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4112. Min Range: -8.4112
Max Act: 7.7237. Min Act: -0.1700
Data Index: 1948563 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4112. Min Range: -8.4112
Max Act: 7.7237. Min Act: -0.1700
Data Index: 4689876 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4112. Min Range: -8.4112
Max Act: 7.7550. Min Act: -0.1700
Data Index: 8501573 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4112. Min Range: -8.4112
Max Act: 7.7237. Min Act: -0.1700
Data Index: 575212 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4112. Min Range: -8.4112
Max Act: 7.7237. Min Act: -0.1700
Data Index: 3537365 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #19