Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2665 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4772. Min Range: -3.4772
Max Act: 3.4772. Min Act: -0.1700
Data Index: 1565535 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4772. Min Range: -3.4772
Max Act: 3.3361. Min Act: -0.1700
Data Index: 4190095 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4772. Min Range: -3.4772
Max Act: 3.3361. Min Act: -0.1700
Data Index: 3185658 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4772. Min Range: -3.4772
Max Act: 3.3204. Min Act: -0.1700
Data Index: 1062607 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4772. Min Range: -3.4772
Max Act: 3.3047. Min Act: -0.1700
Data Index: 1579746 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4772. Min Range: -3.4772
Max Act: 3.3047. Min Act: -0.1700
Data Index: 6054998 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4772. Min Range: -3.4772
Max Act: 3.2890. Min Act: -0.1700
Data Index: 1815743 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4772. Min Range: -3.4772
Max Act: 3.2890. Min Act: -0.1700
Data Index: 3679320 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4772. Min Range: -3.4772
Max Act: 3.2733. Min Act: -0.1700
Data Index: 4101299 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4772. Min Range: -3.4772
Max Act: 3.2733. Min Act: -0.1700
Data Index: 7628084 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4772. Min Range: -3.4772
Max Act: 3.2733. Min Act: -0.1700
Data Index: 3645522 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4772. Min Range: -3.4772
Max Act: 3.2733. Min Act: -0.1700
Data Index: 7599548 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4772. Min Range: -3.4772
Max Act: 3.2733. Min Act: -0.1700
Data Index: 1938412 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4772. Min Range: -3.4772
Max Act: 3.2733. Min Act: -0.1700
Data Index: 3299770 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4772. Min Range: -3.4772
Max Act: 3.2733. Min Act: -0.1700
Data Index: 2209083 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4772. Min Range: -3.4772
Max Act: 3.2576. Min Act: -0.1700
Data Index: 7114754 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4772. Min Range: -3.4772
Max Act: 3.2576. Min Act: -0.1700
Data Index: 1790758 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4772. Min Range: -3.4772
Max Act: 3.2419. Min Act: -0.1700
Data Index: 4991810 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4772. Min Range: -3.4772
Max Act: 3.2419. Min Act: -0.1700
Data Index: 2417987 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4772. Min Range: -3.4772
Max Act: 3.2419. Min Act: -0.1700
Data Index: 3189573 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19