Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5573 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9156. Min Range: -5.9156
Max Act: 5.9156. Min Act: -0.1700
Data Index: 2846773 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9156. Min Range: -5.9156
Max Act: 5.8844. Min Act: -0.1700
Data Index: 6873876 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9156. Min Range: -5.9156
Max Act: 5.8844. Min Act: -0.1700
Data Index: 3571254 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9156. Min Range: -5.9156
Max Act: 5.8219. Min Act: -0.1700
Data Index: 7976156 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9156. Min Range: -5.9156
Max Act: 5.7906. Min Act: -0.1700
Data Index: 7239946 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9156. Min Range: -5.9156
Max Act: 5.8219. Min Act: -0.1700
Data Index: 5126767 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9156. Min Range: -5.9156
Max Act: 5.7906. Min Act: -0.1700
Data Index: 3582318 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9156. Min Range: -5.9156
Max Act: 5.7594. Min Act: -0.1700
Data Index: 6856443 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9156. Min Range: -5.9156
Max Act: 5.7906. Min Act: -0.1700
Data Index: 5414816 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9156. Min Range: -5.9156
Max Act: 5.7281. Min Act: -0.1700
Data Index: 7440404 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9156. Min Range: -5.9156
Max Act: 5.7281. Min Act: -0.1700
Data Index: 6090516 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9156. Min Range: -5.9156
Max Act: 5.6969. Min Act: -0.1700
Data Index: 3133280 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9156. Min Range: -5.9156
Max Act: 5.6656. Min Act: -0.1700
Data Index: 2271124 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9156. Min Range: -5.9156
Max Act: 5.6969. Min Act: -0.1700
Data Index: 5414815 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9156. Min Range: -5.9156
Max Act: 5.6656. Min Act: -0.1700
Data Index: 8519148 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9156. Min Range: -5.9156
Max Act: 5.6656. Min Act: -0.1700
Data Index: 4871705 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9156. Min Range: -5.9156
Max Act: 5.6656. Min Act: -0.1700
Data Index: 2602353 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9156. Min Range: -5.9156
Max Act: 5.6656. Min Act: -0.1700
Data Index: 6733149 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9156. Min Range: -5.9156
Max Act: 5.6656. Min Act: -0.1700
Data Index: 4437068 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9156. Min Range: -5.9156
Max Act: 5.6344. Min Act: -0.1700
Data Index: 1882655 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19