Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1645 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1372. Min Range: -7.1372
Max Act: 7.1372. Min Act: -0.1700
Data Index: 3158126 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1372. Min Range: -7.1372
Max Act: 7.0435. Min Act: -0.1700
Data Index: 4914708 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1372. Min Range: -7.1372
Max Act: 6.9810. Min Act: -0.1700
Data Index: 1994250 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1372. Min Range: -7.1372
Max Act: 6.8872. Min Act: -0.1700
Data Index: 1027910 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1372. Min Range: -7.1372
Max Act: 6.8247. Min Act: -0.1700
Data Index: 5936576 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1372. Min Range: -7.1372
Max Act: 6.8247. Min Act: -0.1700
Data Index: 7707014 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1372. Min Range: -7.1372
Max Act: 6.7935. Min Act: -0.1700
Data Index: 6039325 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1372. Min Range: -7.1372
Max Act: 6.7622. Min Act: -0.1700
Data Index: 5333079 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1372. Min Range: -7.1372
Max Act: 6.7622. Min Act: -0.1700
Data Index: 1941872 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1372. Min Range: -7.1372
Max Act: 6.6060. Min Act: -0.1700
Data Index: 8226954 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1372. Min Range: -7.1372
Max Act: 6.5747. Min Act: -0.1700
Data Index: 951670 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1372. Min Range: -7.1372
Max Act: 6.5747. Min Act: -0.1700
Data Index: 5333604 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1372. Min Range: -7.1372
Max Act: 6.5747. Min Act: -0.1700
Data Index: 6906391 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1372. Min Range: -7.1372
Max Act: 6.5435. Min Act: -0.1700
Data Index: 7316390 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1372. Min Range: -7.1372
Max Act: 6.4810. Min Act: -0.1700
Data Index: 8551518 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1372. Min Range: -7.1372
Max Act: 6.5122. Min Act: -0.1700
Data Index: 6870398 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1372. Min Range: -7.1372
Max Act: 6.5122. Min Act: -0.1700
Data Index: 358675 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1372. Min Range: -7.1372
Max Act: 6.5122. Min Act: -0.1700
Data Index: 2884782 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1372. Min Range: -7.1372
Max Act: 6.4810. Min Act: -0.1700
Data Index: 2686639 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1372. Min Range: -7.1372
Max Act: 6.4810. Min Act: -0.1700
Data Index: 5103156 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #19