Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5086 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.2719. Min Range: -2.2719
Max Act: 2.2719. Min Act: -0.1700
Data Index: 1489730 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2719. Min Range: -2.2719
Max Act: 2.1725. Min Act: -0.1700
Data Index: 4040594 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2719. Min Range: -2.2719
Max Act: 2.1725. Min Act: -0.1700
Data Index: 999422 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2719. Min Range: -2.2719
Max Act: 2.1559. Min Act: -0.1700
Data Index: 1271769 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2719. Min Range: -2.2719
Max Act: 2.1559. Min Act: -0.1700
Data Index: 6238479 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2719. Min Range: -2.2719
Max Act: 2.1392. Min Act: -0.1700
Data Index: 7353548 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2719. Min Range: -2.2719
Max Act: 2.1058. Min Act: -0.1700
Data Index: 730342 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2719. Min Range: -2.2719
Max Act: 2.1058. Min Act: -0.1700
Data Index: 2648172 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2719. Min Range: -2.2719
Max Act: 2.1058. Min Act: -0.1700
Data Index: 1507948 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2719. Min Range: -2.2719
Max Act: 2.1058. Min Act: -0.1700
Data Index: 94836 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2719. Min Range: -2.2719
Max Act: 2.0890. Min Act: -0.1700
Data Index: 2621962 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2719. Min Range: -2.2719
Max Act: 2.0890. Min Act: -0.1700
Data Index: 2071569 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2719. Min Range: -2.2719
Max Act: 2.0890. Min Act: -0.1700
Data Index: 6431123 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2719. Min Range: -2.2719
Max Act: 2.0890. Min Act: -0.1700
Data Index: 2710637 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2719. Min Range: -2.2719
Max Act: 2.0890. Min Act: -0.1700
Data Index: 7734238 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2719. Min Range: -2.2719
Max Act: 2.0890. Min Act: -0.1700
Data Index: 5031507 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2719. Min Range: -2.2719
Max Act: 2.0890. Min Act: -0.1700
Data Index: 7053115 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2719. Min Range: -2.2719
Max Act: 2.0890. Min Act: -0.1700
Data Index: 752058 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2719. Min Range: -2.2719
Max Act: 2.0722. Min Act: -0.1700
Data Index: 1925119 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2719. Min Range: -2.2719
Max Act: 2.0722. Min Act: -0.1700
Data Index: 1600817 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #19