Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3211 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2275. Min Range: -3.2275
Max Act: 3.2275. Min Act: -0.1700
Data Index: 1378448 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2275. Min Range: -3.2275
Max Act: 3.2118. Min Act: -0.1700
Data Index: 2248580 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2275. Min Range: -3.2275
Max Act: 3.1331. Min Act: -0.1700
Data Index: 3152132 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2275. Min Range: -3.2275
Max Act: 3.1016. Min Act: -0.1700
Data Index: 6662246 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2275. Min Range: -3.2275
Max Act: 3.1016. Min Act: -0.1700
Data Index: 6007922 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2275. Min Range: -3.2275
Max Act: 3.0701. Min Act: -0.1700
Data Index: 6459296 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2275. Min Range: -3.2275
Max Act: 3.0543. Min Act: -0.1700
Data Index: 3976568 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2275. Min Range: -3.2275
Max Act: 3.0543. Min Act: -0.1700
Data Index: 1486439 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2275. Min Range: -3.2275
Max Act: 3.0385. Min Act: -0.1700
Data Index: 926704 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2275. Min Range: -3.2275
Max Act: 3.0385. Min Act: -0.1700
Data Index: 8571815 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2275. Min Range: -3.2275
Max Act: 3.0385. Min Act: -0.1700
Data Index: 6222255 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2275. Min Range: -3.2275
Max Act: 3.0227. Min Act: -0.1700
Data Index: 6401874 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2275. Min Range: -3.2275
Max Act: 3.0227. Min Act: -0.1700
Data Index: 6007928 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2275. Min Range: -3.2275
Max Act: 3.0227. Min Act: -0.1700
Data Index: 5750316 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2275. Min Range: -3.2275
Max Act: 3.0227. Min Act: -0.1700
Data Index: 7731992 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2275. Min Range: -3.2275
Max Act: 3.0227. Min Act: -0.1700
Data Index: 8016845 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2275. Min Range: -3.2275
Max Act: 3.0227. Min Act: -0.1700
Data Index: 4961052 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2275. Min Range: -3.2275
Max Act: 3.0227. Min Act: -0.1700
Data Index: 1218453 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2275. Min Range: -3.2275
Max Act: 3.0069. Min Act: -0.1700
Data Index: 601658 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2275. Min Range: -3.2275
Max Act: 3.0069. Min Act: -0.1700
Data Index: 4251 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19